Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 55 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 12.4720. Min Range: -12.4720
Max Act: 12.4720. Min Act: -0.1700
Data Index: 5763345 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.4720. Min Range: -12.4720
Max Act: 12.4720. Min Act: -0.1700
Data Index: 5763344 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.4720. Min Range: -12.4720
Max Act: 12.2845. Min Act: -0.1700
Data Index: 5763340 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.4720. Min Range: -12.4720
Max Act: 12.0970. Min Act: -0.1700
Data Index: 5763342 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.4720. Min Range: -12.4720
Max Act: 12.0970. Min Act: -0.1700
Data Index: 124776 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.4720. Min Range: -12.4720
Max Act: 12.0970. Min Act: -0.1700
Data Index: 5763343 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.4720. Min Range: -12.4720
Max Act: 12.0970. Min Act: -0.1700
Data Index: 7119798 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.4720. Min Range: -12.4720
Max Act: 12.0345. Min Act: -0.1700
Data Index: 6123603 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.4720. Min Range: -12.4720
Max Act: 12.0345. Min Act: -0.1700
Data Index: 4247081 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.4720. Min Range: -12.4720
Max Act: 12.0970. Min Act: -0.1700
Data Index: 8384655 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.4720. Min Range: -12.4720
Max Act: 11.9720. Min Act: -0.1700
Data Index: 7119797 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.4720. Min Range: -12.4720
Max Act: 12.0345. Min Act: -0.1700
Data Index: 5763339 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.4720. Min Range: -12.4720
Max Act: 11.9095. Min Act: -0.1700
Data Index: 5763360 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.4720. Min Range: -12.4720
Max Act: 11.8470. Min Act: -0.1700
Data Index: 4958428 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.4720. Min Range: -12.4720
Max Act: 11.8470. Min Act: -0.1700
Data Index: 5763351 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.4720. Min Range: -12.4720
Max Act: 11.8470. Min Act: -0.1700
Data Index: 5763368 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.4720. Min Range: -12.4720
Max Act: 11.8470. Min Act: -0.1700
Data Index: 432886 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.4720. Min Range: -12.4720
Max Act: 11.8470. Min Act: -0.1700
Data Index: 6123602 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.4720. Min Range: -12.4720
Max Act: 11.8470. Min Act: -0.1700
Data Index: 7049500 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.4720. Min Range: -12.4720
Max Act: 11.7845. Min Act: -0.1700
Data Index: 5763370 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19