Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 496 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7169. Min Range: -9.7169
Max Act: 9.7169. Min Act: -0.1700
Data Index: 4834177 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7169. Min Range: -9.7169
Max Act: 9.6544. Min Act: -0.1700
Data Index: 214981 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7169. Min Range: -9.7169
Max Act: 9.6544. Min Act: -0.1700
Data Index: 3799993 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7169. Min Range: -9.7169
Max Act: 9.5919. Min Act: -0.1700
Data Index: 5991496 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7169. Min Range: -9.7169
Max Act: 9.5919. Min Act: -0.1700
Data Index: 5656479 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7169. Min Range: -9.7169
Max Act: 9.5919. Min Act: -0.1700
Data Index: 6340932 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7169. Min Range: -9.7169
Max Act: 9.5294. Min Act: -0.1700
Data Index: 5981059 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7169. Min Range: -9.7169
Max Act: 9.4669. Min Act: -0.1700
Data Index: 5981058 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7169. Min Range: -9.7169
Max Act: 9.4669. Min Act: -0.1700
Data Index: 7878215 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7169. Min Range: -9.7169
Max Act: 9.4669. Min Act: -0.1700
Data Index: 2214399 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7169. Min Range: -9.7169
Max Act: 9.4044. Min Act: -0.1700
Data Index: 3377022 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7169. Min Range: -9.7169
Max Act: 9.4044. Min Act: -0.1700
Data Index: 6392871 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7169. Min Range: -9.7169
Max Act: 9.3419. Min Act: -0.1700
Data Index: 2146169 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7169. Min Range: -9.7169
Max Act: 9.2169. Min Act: -0.1700
Data Index: 4318081 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7169. Min Range: -9.7169
Max Act: 9.2169. Min Act: -0.1700
Data Index: 2214398 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7169. Min Range: -9.7169
Max Act: 9.2169. Min Act: -0.1700
Data Index: 5656478 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7169. Min Range: -9.7169
Max Act: 9.1544. Min Act: -0.1700
Data Index: 2349195 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7169. Min Range: -9.7169
Max Act: 9.1544. Min Act: -0.1700
Data Index: 6529101 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7169. Min Range: -9.7169
Max Act: 9.1544. Min Act: -0.1700
Data Index: 3240699 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7169. Min Range: -9.7169
Max Act: 9.1544. Min Act: -0.1700
Data Index: 337231 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19