Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3885 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2637. Min Range: -6.2637
Max Act: 6.2637. Min Act: -0.1700
Data Index: 7520452 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2637. Min Range: -6.2637
Max Act: 6.1074. Min Act: -0.1700
Data Index: 3783184 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2637. Min Range: -6.2637
Max Act: 5.8262. Min Act: -0.1700
Data Index: 8621308 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2637. Min Range: -6.2637
Max Act: 5.7637. Min Act: -0.1700
Data Index: 613648 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2637. Min Range: -6.2637
Max Act: 5.7637. Min Act: -0.1700
Data Index: 6212985 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2637. Min Range: -6.2637
Max Act: 5.7949. Min Act: -0.1700
Data Index: 4981787 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2637. Min Range: -6.2637
Max Act: 5.7324. Min Act: -0.1700
Data Index: 5103166 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2637. Min Range: -6.2637
Max Act: 5.7012. Min Act: -0.1700
Data Index: 794444 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2637. Min Range: -6.2637
Max Act: 5.7012. Min Act: -0.1700
Data Index: 6879260 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2637. Min Range: -6.2637
Max Act: 5.6699. Min Act: -0.1700
Data Index: 3520194 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2637. Min Range: -6.2637
Max Act: 5.7012. Min Act: -0.1700
Data Index: 8423803 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2637. Min Range: -6.2637
Max Act: 5.6699. Min Act: -0.1700
Data Index: 4804103 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2637. Min Range: -6.2637
Max Act: 5.7012. Min Act: -0.1700
Data Index: 1736078 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2637. Min Range: -6.2637
Max Act: 5.6699. Min Act: -0.1700
Data Index: 4791496 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2637. Min Range: -6.2637
Max Act: 5.6387. Min Act: -0.1700
Data Index: 2259195 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2637. Min Range: -6.2637
Max Act: 5.6699. Min Act: -0.1700
Data Index: 6749272 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2637. Min Range: -6.2637
Max Act: 5.6387. Min Act: -0.1700
Data Index: 8387161 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2637. Min Range: -6.2637
Max Act: 5.5449. Min Act: -0.1700
Data Index: 3090221 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2637. Min Range: -6.2637
Max Act: 5.6074. Min Act: -0.1700
Data Index: 6233053 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2637. Min Range: -6.2637
Max Act: 5.5762. Min Act: -0.1700
Data Index: 7621332 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19