Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3173 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5038. Min Range: -5.5038
Max Act: 5.5038. Min Act: -0.1700
Data Index: 1709187 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5038. Min Range: -5.5038
Max Act: 5.4413. Min Act: -0.1700
Data Index: 3030790 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5038. Min Range: -5.5038
Max Act: 5.4101. Min Act: -0.1700
Data Index: 3823578 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5038. Min Range: -5.5038
Max Act: 5.3476. Min Act: -0.1700
Data Index: 5682263 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5038. Min Range: -5.5038
Max Act: 5.2851. Min Act: -0.1700
Data Index: 3008394 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5038. Min Range: -5.5038
Max Act: 5.2538. Min Act: -0.1700
Data Index: 7099357 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5038. Min Range: -5.5038
Max Act: 5.2538. Min Act: -0.1700
Data Index: 1418994 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5038. Min Range: -5.5038
Max Act: 5.2226. Min Act: -0.1700
Data Index: 8191271 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5038. Min Range: -5.5038
Max Act: 5.2226. Min Act: -0.1700
Data Index: 715761 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5038. Min Range: -5.5038
Max Act: 5.2226. Min Act: -0.1700
Data Index: 2789021 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5038. Min Range: -5.5038
Max Act: 5.1913. Min Act: -0.1700
Data Index: 5026207 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5038. Min Range: -5.5038
Max Act: 5.1601. Min Act: -0.1700
Data Index: 8612496 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5038. Min Range: -5.5038
Max Act: 5.1913. Min Act: -0.1700
Data Index: 8787928 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5038. Min Range: -5.5038
Max Act: 5.1913. Min Act: -0.1700
Data Index: 3876215 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5038. Min Range: -5.5038
Max Act: 5.1913. Min Act: -0.1700
Data Index: 6489400 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5038. Min Range: -5.5038
Max Act: 5.1601. Min Act: -0.1700
Data Index: 408575 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5038. Min Range: -5.5038
Max Act: 5.1288. Min Act: -0.1700
Data Index: 5838555 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5038. Min Range: -5.5038
Max Act: 5.1288. Min Act: -0.1700
Data Index: 3057468 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5038. Min Range: -5.5038
Max Act: 5.1288. Min Act: -0.1700
Data Index: 8762307 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5038. Min Range: -5.5038
Max Act: 5.1288. Min Act: -0.1700
Data Index: 676731 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19