Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 672 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3117. Min Range: -5.3117
Max Act: 5.3117. Min Act: -0.1700
Data Index: 3835245 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3117. Min Range: -5.3117
Max Act: 5.2492. Min Act: -0.1700
Data Index: 6765537 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3117. Min Range: -5.3117
Max Act: 5.2492. Min Act: -0.1700
Data Index: 6751324 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3117. Min Range: -5.3117
Max Act: 5.0929. Min Act: -0.1700
Data Index: 6751326 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3117. Min Range: -5.3117
Max Act: 5.0929. Min Act: -0.1700
Data Index: 6751319 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3117. Min Range: -5.3117
Max Act: 5.0304. Min Act: -0.1700
Data Index: 475006 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3117. Min Range: -5.3117
Max Act: 4.9679. Min Act: -0.1700
Data Index: 1688100 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3117. Min Range: -5.3117
Max Act: 4.9992. Min Act: -0.1700
Data Index: 2291122 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3117. Min Range: -5.3117
Max Act: 4.9054. Min Act: -0.1700
Data Index: 5151689 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3117. Min Range: -5.3117
Max Act: 4.9054. Min Act: -0.1700
Data Index: 7172004 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3117. Min Range: -5.3117
Max Act: 4.9367. Min Act: -0.1700
Data Index: 6751327 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3117. Min Range: -5.3117
Max Act: 4.9054. Min Act: -0.1700
Data Index: 5206854 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3117. Min Range: -5.3117
Max Act: 4.8117. Min Act: -0.1700
Data Index: 7917447 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3117. Min Range: -5.3117
Max Act: 4.7492. Min Act: -0.1700
Data Index: 8103113 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3117. Min Range: -5.3117
Max Act: 4.7492. Min Act: -0.1700
Data Index: 3835246 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3117. Min Range: -5.3117
Max Act: 4.7179. Min Act: -0.1700
Data Index: 642310 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3117. Min Range: -5.3117
Max Act: 4.7179. Min Act: -0.1700
Data Index: 3649737 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3117. Min Range: -5.3117
Max Act: 4.7179. Min Act: -0.1700
Data Index: 1163416 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3117. Min Range: -5.3117
Max Act: 4.6867. Min Act: -0.1700
Data Index: 6833733 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3117. Min Range: -5.3117
Max Act: 4.6867. Min Act: -0.1700
Data Index: 2031465 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19