Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5881 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7991. Min Range: -6.7991
Max Act: 6.7991. Min Act: -0.1700
Data Index: 3988036 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7991. Min Range: -6.7991
Max Act: 6.7991. Min Act: -0.1700
Data Index: 5693049 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7991. Min Range: -6.7991
Max Act: 6.7054. Min Act: -0.1700
Data Index: 5789067 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7991. Min Range: -6.7991
Max Act: 6.5491. Min Act: -0.1700
Data Index: 2890930 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7991. Min Range: -6.7991
Max Act: 6.5491. Min Act: -0.1700
Data Index: 758472 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7991. Min Range: -6.7991
Max Act: 6.5491. Min Act: -0.1700
Data Index: 1857212 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7991. Min Range: -6.7991
Max Act: 6.4866. Min Act: -0.1700
Data Index: 1463220 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7991. Min Range: -6.7991
Max Act: 6.5179. Min Act: -0.1700
Data Index: 1790731 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7991. Min Range: -6.7991
Max Act: 6.5179. Min Act: -0.1700
Data Index: 1982387 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7991. Min Range: -6.7991
Max Act: 6.4866. Min Act: -0.1700
Data Index: 3169754 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7991. Min Range: -6.7991
Max Act: 6.5179. Min Act: -0.1700
Data Index: 2152974 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7991. Min Range: -6.7991
Max Act: 6.4866. Min Act: -0.1700
Data Index: 6722184 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7991. Min Range: -6.7991
Max Act: 6.4866. Min Act: -0.1700
Data Index: 4242597 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7991. Min Range: -6.7991
Max Act: 6.4554. Min Act: -0.1700
Data Index: 4305905 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7991. Min Range: -6.7991
Max Act: 6.4554. Min Act: -0.1700
Data Index: 4902217 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7991. Min Range: -6.7991
Max Act: 6.4241. Min Act: -0.1700
Data Index: 566383 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7991. Min Range: -6.7991
Max Act: 6.3929. Min Act: -0.1700
Data Index: 5971975 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7991. Min Range: -6.7991
Max Act: 6.3929. Min Act: -0.1700
Data Index: 3670102 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7991. Min Range: -6.7991
Max Act: 6.4241. Min Act: -0.1700
Data Index: 8015705 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7991. Min Range: -6.7991
Max Act: 6.4241. Min Act: -0.1700
Data Index: 7946010 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19