Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 687 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9392. Min Range: -7.9392
Max Act: 7.9392. Min Act: -0.1700
Data Index: 1008493 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9392. Min Range: -7.9392
Max Act: 7.4704. Min Act: -0.1700
Data Index: 5299789 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9392. Min Range: -7.9392
Max Act: 7.3767. Min Act: -0.1700
Data Index: 3251279 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9392. Min Range: -7.9392
Max Act: 7.1579. Min Act: -0.1700
Data Index: 5645562 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9392. Min Range: -7.9392
Max Act: 7.0954. Min Act: -0.1700
Data Index: 3406904 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9392. Min Range: -7.9392
Max Act: 7.0017. Min Act: -0.1700
Data Index: 7116819 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9392. Min Range: -7.9392
Max Act: 7.0017. Min Act: -0.1700
Data Index: 6355508 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9392. Min Range: -7.9392
Max Act: 6.9704. Min Act: -0.1700
Data Index: 1418266 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9392. Min Range: -7.9392
Max Act: 6.9392. Min Act: -0.1700
Data Index: 3392579 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9392. Min Range: -7.9392
Max Act: 6.9392. Min Act: -0.1700
Data Index: 3741378 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9392. Min Range: -7.9392
Max Act: 6.9079. Min Act: -0.1700
Data Index: 7466504 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9392. Min Range: -7.9392
Max Act: 6.9079. Min Act: -0.1700
Data Index: 6613036 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9392. Min Range: -7.9392
Max Act: 6.8767. Min Act: -0.1700
Data Index: 2153309 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9392. Min Range: -7.9392
Max Act: 6.8767. Min Act: -0.1700
Data Index: 4796682 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9392. Min Range: -7.9392
Max Act: 6.9079. Min Act: -0.1700
Data Index: 7956204 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9392. Min Range: -7.9392
Max Act: 6.8767. Min Act: -0.1700
Data Index: 4385251 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9392. Min Range: -7.9392
Max Act: 6.8454. Min Act: -0.1700
Data Index: 1186120 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9392. Min Range: -7.9392
Max Act: 6.8454. Min Act: -0.1700
Data Index: 5063829 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9392. Min Range: -7.9392
Max Act: 6.8142. Min Act: -0.1700
Data Index: 8373357 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9392. Min Range: -7.9392
Max Act: 6.8142. Min Act: -0.1700
Data Index: 3676169 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19