Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 621 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5171. Min Range: -6.5171
Max Act: 6.5171. Min Act: -0.1700
Data Index: 7461828 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5171. Min Range: -6.5171
Max Act: 6.0483. Min Act: -0.1700
Data Index: 8257999 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5171. Min Range: -6.5171
Max Act: 5.9233. Min Act: -0.1700
Data Index: 5254850 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5171. Min Range: -6.5171
Max Act: 5.8921. Min Act: -0.1700
Data Index: 5860582 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5171. Min Range: -6.5171
Max Act: 5.8296. Min Act: -0.1700
Data Index: 4076014 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5171. Min Range: -6.5171
Max Act: 5.7358. Min Act: -0.1700
Data Index: 3321582 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5171. Min Range: -6.5171
Max Act: 5.6421. Min Act: -0.1700
Data Index: 3895613 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5171. Min Range: -6.5171
Max Act: 5.5796. Min Act: -0.1700
Data Index: 5786716 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5171. Min Range: -6.5171
Max Act: 5.5483. Min Act: -0.1700
Data Index: 5556603 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5171. Min Range: -6.5171
Max Act: 5.5483. Min Act: -0.1700
Data Index: 6449340 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5171. Min Range: -6.5171
Max Act: 5.5483. Min Act: -0.1700
Data Index: 4966846 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5171. Min Range: -6.5171
Max Act: 5.5483. Min Act: -0.1700
Data Index: 777305 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5171. Min Range: -6.5171
Max Act: 5.5483. Min Act: -0.1700
Data Index: 7074400 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5171. Min Range: -6.5171
Max Act: 5.5171. Min Act: -0.1700
Data Index: 6865252 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5171. Min Range: -6.5171
Max Act: 5.4858. Min Act: -0.1700
Data Index: 8310734 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5171. Min Range: -6.5171
Max Act: 5.4858. Min Act: -0.1700
Data Index: 2983414 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5171. Min Range: -6.5171
Max Act: 5.4858. Min Act: -0.1700
Data Index: 5146577 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5171. Min Range: -6.5171
Max Act: 5.5171. Min Act: -0.1700
Data Index: 2347218 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5171. Min Range: -6.5171
Max Act: 5.4546. Min Act: -0.1700
Data Index: 7373797 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5171. Min Range: -6.5171
Max Act: 5.4858. Min Act: -0.1700
Data Index: 2570403 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19