Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3235 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7443. Min Range: -3.7443
Max Act: 3.7443. Min Act: -0.1700
Data Index: 4010140 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7443. Min Range: -3.7443
Max Act: 3.7130. Min Act: -0.1700
Data Index: 6473774 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7443. Min Range: -3.7443
Max Act: 3.6192. Min Act: -0.1700
Data Index: 3247604 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7443. Min Range: -3.7443
Max Act: 3.6505. Min Act: -0.1700
Data Index: 5243597 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7443. Min Range: -3.7443
Max Act: 3.5879. Min Act: -0.1700
Data Index: 5140988 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7443. Min Range: -3.7443
Max Act: 3.5409. Min Act: -0.1700
Data Index: 8343625 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7443. Min Range: -3.7443
Max Act: 3.5409. Min Act: -0.1700
Data Index: 6101376 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7443. Min Range: -3.7443
Max Act: 3.5096. Min Act: -0.1700
Data Index: 8205040 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7443. Min Range: -3.7443
Max Act: 3.5096. Min Act: -0.1700
Data Index: 2600089 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7443. Min Range: -3.7443
Max Act: 3.4939. Min Act: -0.1700
Data Index: 2570041 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7443. Min Range: -3.7443
Max Act: 3.5096. Min Act: -0.1700
Data Index: 2290783 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7443. Min Range: -3.7443
Max Act: 3.4939. Min Act: -0.1700
Data Index: 3335044 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7443. Min Range: -3.7443
Max Act: 3.4939. Min Act: -0.1700
Data Index: 1687489 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7443. Min Range: -3.7443
Max Act: 3.5096. Min Act: -0.1700
Data Index: 6049798 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7443. Min Range: -3.7443
Max Act: 3.4782. Min Act: -0.1700
Data Index: 8822001 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7443. Min Range: -3.7443
Max Act: 3.4626. Min Act: -0.1700
Data Index: 7175207 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7443. Min Range: -3.7443
Max Act: 3.4939. Min Act: -0.1700
Data Index: 1040541 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7443. Min Range: -3.7443
Max Act: 3.4469. Min Act: -0.1700
Data Index: 473702 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7443. Min Range: -3.7443
Max Act: 3.4626. Min Act: -0.1700
Data Index: 1763390 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7443. Min Range: -3.7443
Max Act: 3.4626. Min Act: -0.1700
Data Index: 75868 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19