Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5211 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5035. Min Range: -7.5035
Max Act: 7.5035. Min Act: -0.1700
Data Index: 6131940 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5035. Min Range: -7.5035
Max Act: 7.2535. Min Act: -0.1700
Data Index: 8454869 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5035. Min Range: -7.5035
Max Act: 7.1910. Min Act: -0.1700
Data Index: 3125319 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5035. Min Range: -7.5035
Max Act: 7.0972. Min Act: -0.1700
Data Index: 6572787 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5035. Min Range: -7.5035
Max Act: 7.0347. Min Act: -0.1700
Data Index: 7597472 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5035. Min Range: -7.5035
Max Act: 7.0347. Min Act: -0.1700
Data Index: 6860716 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5035. Min Range: -7.5035
Max Act: 7.0347. Min Act: -0.1700
Data Index: 1591308 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5035. Min Range: -7.5035
Max Act: 6.9722. Min Act: -0.1700
Data Index: 3251114 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5035. Min Range: -7.5035
Max Act: 6.9410. Min Act: -0.1700
Data Index: 3773353 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5035. Min Range: -7.5035
Max Act: 6.9097. Min Act: -0.1700
Data Index: 1714651 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5035. Min Range: -7.5035
Max Act: 6.9097. Min Act: -0.1700
Data Index: 4025798 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5035. Min Range: -7.5035
Max Act: 6.9097. Min Act: -0.1700
Data Index: 7527132 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5035. Min Range: -7.5035
Max Act: 6.8472. Min Act: -0.1700
Data Index: 5212270 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5035. Min Range: -7.5035
Max Act: 6.8472. Min Act: -0.1700
Data Index: 3566979 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5035. Min Range: -7.5035
Max Act: 6.8160. Min Act: -0.1700
Data Index: 1530901 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5035. Min Range: -7.5035
Max Act: 6.7535. Min Act: -0.1700
Data Index: 494989 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5035. Min Range: -7.5035
Max Act: 6.7847. Min Act: -0.1700
Data Index: 7074009 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5035. Min Range: -7.5035
Max Act: 6.7847. Min Act: -0.1700
Data Index: 5428297 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5035. Min Range: -7.5035
Max Act: 6.7535. Min Act: -0.1700
Data Index: 3971629 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5035. Min Range: -7.5035
Max Act: 6.7222. Min Act: -0.1700
Data Index: 4681532 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19