Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3763 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.7402. Min Act: -0.1700
Data Index: 1169937 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.6307. Min Act: -0.1700
Data Index: 3287304 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.5524. Min Act: -0.1700
Data Index: 51350 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.4585. Min Act: -0.1700
Data Index: 7802220 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.4271. Min Act: -0.1700
Data Index: 7331085 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.4114. Min Act: -0.1700
Data Index: 7469087 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.4114. Min Act: -0.1700
Data Index: 725253 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.4114. Min Act: -0.1700
Data Index: 3057147 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.3801. Min Act: -0.1700
Data Index: 5839605 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.3958. Min Act: -0.1700
Data Index: 5470508 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.3487. Min Act: -0.1700
Data Index: 8189114 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.3644. Min Act: -0.1700
Data Index: 6783087 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.3330. Min Act: -0.1700
Data Index: 407592 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.3487. Min Act: -0.1700
Data Index: 1281243 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.3487. Min Act: -0.1700
Data Index: 2603670 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.3173. Min Act: -0.1700
Data Index: 8554590 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.3016. Min Act: -0.1700
Data Index: 2208412 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.3016. Min Act: -0.1700
Data Index: 3438357 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.3016. Min Act: -0.1700
Data Index: 5928714 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.3016. Min Act: -0.1700
Data Index: 5897276 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19