Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3981 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3128. Min Range: -5.3128
Max Act: 5.3128. Min Act: -0.1700
Data Index: 7937084 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3128. Min Range: -5.3128
Max Act: 5.1565. Min Act: -0.1700
Data Index: 8013398 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3128. Min Range: -5.3128
Max Act: 5.0940. Min Act: -0.1700
Data Index: 2933145 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3128. Min Range: -5.3128
Max Act: 5.0940. Min Act: -0.1700
Data Index: 7204918 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3128. Min Range: -5.3128
Max Act: 5.0003. Min Act: -0.1700
Data Index: 8581776 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3128. Min Range: -5.3128
Max Act: 4.9378. Min Act: -0.1700
Data Index: 995779 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3128. Min Range: -5.3128
Max Act: 4.9378. Min Act: -0.1700
Data Index: 8661493 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3128. Min Range: -5.3128
Max Act: 4.9065. Min Act: -0.1700
Data Index: 7311305 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3128. Min Range: -5.3128
Max Act: 4.9378. Min Act: -0.1700
Data Index: 4427213 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3128. Min Range: -5.3128
Max Act: 4.8440. Min Act: -0.1700
Data Index: 4101142 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3128. Min Range: -5.3128
Max Act: 4.8440. Min Act: -0.1700
Data Index: 6795858 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3128. Min Range: -5.3128
Max Act: 4.8128. Min Act: -0.1700
Data Index: 491346 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3128. Min Range: -5.3128
Max Act: 4.7815. Min Act: -0.1700
Data Index: 6611885 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3128. Min Range: -5.3128
Max Act: 4.8128. Min Act: -0.1700
Data Index: 2312983 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3128. Min Range: -5.3128
Max Act: 4.8128. Min Act: -0.1700
Data Index: 1131538 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3128. Min Range: -5.3128
Max Act: 4.7503. Min Act: -0.1700
Data Index: 3120249 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3128. Min Range: -5.3128
Max Act: 4.7503. Min Act: -0.1700
Data Index: 1271395 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3128. Min Range: -5.3128
Max Act: 4.7190. Min Act: -0.1700
Data Index: 8550839 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3128. Min Range: -5.3128
Max Act: 4.6878. Min Act: -0.1700
Data Index: 953597 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3128. Min Range: -5.3128
Max Act: 4.6878. Min Act: -0.1700
Data Index: 4520666 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19