Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5451 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6347. Min Range: -6.6347
Max Act: 6.6347. Min Act: -0.1700
Data Index: 7422820 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6347. Min Range: -6.6347
Max Act: 6.4160. Min Act: -0.1700
Data Index: 702512 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6347. Min Range: -6.6347
Max Act: 6.1972. Min Act: -0.1700
Data Index: 5191112 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6347. Min Range: -6.6347
Max Act: 6.1347. Min Act: -0.1700
Data Index: 4786049 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6347. Min Range: -6.6347
Max Act: 6.1035. Min Act: -0.1700
Data Index: 2918204 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6347. Min Range: -6.6347
Max Act: 5.9472. Min Act: -0.1700
Data Index: 1750844 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6347. Min Range: -6.6347
Max Act: 5.9472. Min Act: -0.1700
Data Index: 5534738 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6347. Min Range: -6.6347
Max Act: 5.8847. Min Act: -0.1700
Data Index: 3024053 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6347. Min Range: -6.6347
Max Act: 5.8535. Min Act: -0.1700
Data Index: 2675472 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6347. Min Range: -6.6347
Max Act: 5.8535. Min Act: -0.1700
Data Index: 4966039 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6347. Min Range: -6.6347
Max Act: 5.8535. Min Act: -0.1700
Data Index: 668181 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6347. Min Range: -6.6347
Max Act: 5.8222. Min Act: -0.1700
Data Index: 621193 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6347. Min Range: -6.6347
Max Act: 5.8222. Min Act: -0.1700
Data Index: 220012 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6347. Min Range: -6.6347
Max Act: 5.8222. Min Act: -0.1700
Data Index: 5437189 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6347. Min Range: -6.6347
Max Act: 5.7910. Min Act: -0.1700
Data Index: 7034339 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6347. Min Range: -6.6347
Max Act: 5.7910. Min Act: -0.1700
Data Index: 6548433 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6347. Min Range: -6.6347
Max Act: 5.7285. Min Act: -0.1700
Data Index: 5100509 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6347. Min Range: -6.6347
Max Act: 5.6972. Min Act: -0.1700
Data Index: 1991082 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6347. Min Range: -6.6347
Max Act: 5.6660. Min Act: -0.1700
Data Index: 3983533 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6347. Min Range: -6.6347
Max Act: 5.6660. Min Act: -0.1700
Data Index: 1067895 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19