Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 389 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5124. Min Range: -1.5124
Max Act: 1.5124. Min Act: -0.1700
Data Index: 4501729 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5124. Min Range: -1.5124
Max Act: 1.4948. Min Act: -0.1700
Data Index: 6153126 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5124. Min Range: -1.5124
Max Act: 1.4861. Min Act: -0.1699
Data Index: 2696193 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5124. Min Range: -1.5124
Max Act: 1.4861. Min Act: -0.1700
Data Index: 4501731 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5124. Min Range: -1.5124
Max Act: 1.4773. Min Act: -0.1700
Data Index: 7846596 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5124. Min Range: -1.5124
Max Act: 1.4597. Min Act: -0.1700
Data Index: 6215409 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5124. Min Range: -1.5124
Max Act: 1.4509. Min Act: -0.1699
Data Index: 6751809 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5124. Min Range: -1.5124
Max Act: 1.4597. Min Act: -0.1700
Data Index: 6153140 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5124. Min Range: -1.5124
Max Act: 1.4421. Min Act: -0.1700
Data Index: 2887308 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5124. Min Range: -1.5124
Max Act: 1.4509. Min Act: -0.1700
Data Index: 6667267 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5124. Min Range: -1.5124
Max Act: 1.4509. Min Act: -0.1700
Data Index: 4937246 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5124. Min Range: -1.5124
Max Act: 1.4421. Min Act: -0.1700
Data Index: 4821163 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5124. Min Range: -1.5124
Max Act: 1.4421. Min Act: -0.1692
Data Index: 278324 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5124. Min Range: -1.5124
Max Act: 1.4333. Min Act: -0.1700
Data Index: 7135432 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5124. Min Range: -1.5124
Max Act: 1.4333. Min Act: -0.1700
Data Index: 29704 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5124. Min Range: -1.5124
Max Act: 1.4333. Min Act: -0.1700
Data Index: 4501721 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5124. Min Range: -1.5124
Max Act: 1.4333. Min Act: -0.1698
Data Index: 8114204 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5124. Min Range: -1.5124
Max Act: 1.4333. Min Act: -0.1697
Data Index: 3155609 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5124. Min Range: -1.5124
Max Act: 1.4333. Min Act: -0.1700
Data Index: 680766 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5124. Min Range: -1.5124
Max Act: 1.4245. Min Act: -0.1699
Data Index: 5790370 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #19