Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6210 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0542. Min Range: -4.0542
Max Act: 4.0542. Min Act: -0.1700
Data Index: 931975 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0542. Min Range: -4.0542
Max Act: 4.0230. Min Act: -0.1700
Data Index: 7181468 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.9917. Min Act: -0.1700
Data Index: 931974 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.9917. Min Act: -0.1700
Data Index: 7232555 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.9292. Min Act: -0.1700
Data Index: 3469294 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.9292. Min Act: -0.1700
Data Index: 7864666 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.9292. Min Act: -0.1700
Data Index: 3133689 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.9292. Min Act: -0.1700
Data Index: 8167565 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.9292. Min Act: -0.1700
Data Index: 6725497 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.9292. Min Act: -0.1700
Data Index: 7181467 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.9292. Min Act: -0.1700
Data Index: 432063 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.8667. Min Act: -0.1700
Data Index: 7864667 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.8667. Min Act: -0.1700
Data Index: 8385480 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.8667. Min Act: -0.1700
Data Index: 3541102 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.8979. Min Act: -0.1700
Data Index: 8747317 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.8979. Min Act: -0.1700
Data Index: 8593177 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.8979. Min Act: -0.1700
Data Index: 1972894 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.8667. Min Act: -0.1700
Data Index: 7181470 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.8667. Min Act: -0.1700
Data Index: 5096518 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0542. Min Range: -4.0542
Max Act: 3.8667. Min Act: -0.1700
Data Index: 3330473 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19