Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 625 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9896. Min Range: -6.9896
Max Act: 6.9896. Min Act: -0.1700
Data Index: 3927554 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9896. Min Range: -6.9896
Max Act: 6.9583. Min Act: -0.1700
Data Index: 4472329 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9896. Min Range: -6.9896
Max Act: 6.7083. Min Act: -0.1700
Data Index: 7230079 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9896. Min Range: -6.9896
Max Act: 6.4271. Min Act: -0.1700
Data Index: 8550804 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9896. Min Range: -6.9896
Max Act: 6.4896. Min Act: -0.1700
Data Index: 581589 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9896. Min Range: -6.9896
Max Act: 6.3646. Min Act: -0.1700
Data Index: 2125858 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9896. Min Range: -6.9896
Max Act: 6.3333. Min Act: -0.1700
Data Index: 530681 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9896. Min Range: -6.9896
Max Act: 6.3333. Min Act: -0.1700
Data Index: 6369446 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9896. Min Range: -6.9896
Max Act: 6.3333. Min Act: -0.1700
Data Index: 4163283 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9896. Min Range: -6.9896
Max Act: 6.3021. Min Act: -0.1700
Data Index: 4496037 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9896. Min Range: -6.9896
Max Act: 6.3333. Min Act: -0.1700
Data Index: 4812809 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9896. Min Range: -6.9896
Max Act: 6.3021. Min Act: -0.1700
Data Index: 3949989 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9896. Min Range: -6.9896
Max Act: 6.2708. Min Act: -0.1700
Data Index: 2194987 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9896. Min Range: -6.9896
Max Act: 6.3333. Min Act: -0.1700
Data Index: 6359896 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9896. Min Range: -6.9896
Max Act: 6.2396. Min Act: -0.1700
Data Index: 814871 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9896. Min Range: -6.9896
Max Act: 6.2708. Min Act: -0.1700
Data Index: 5328138 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9896. Min Range: -6.9896
Max Act: 6.3021. Min Act: -0.1700
Data Index: 7294519 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9896. Min Range: -6.9896
Max Act: 6.2396. Min Act: -0.1700
Data Index: 3014929 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9896. Min Range: -6.9896
Max Act: 6.2708. Min Act: -0.1700
Data Index: 1410028 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9896. Min Range: -6.9896
Max Act: 6.2083. Min Act: -0.1700
Data Index: 5967685 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19