Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6122 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5035. Min Range: -4.5035
Max Act: 4.5035. Min Act: -0.1700
Data Index: 6136885 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5035. Min Range: -4.5035
Max Act: 4.3785. Min Act: -0.1700
Data Index: 7269138 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5035. Min Range: -4.5035
Max Act: 4.3785. Min Act: -0.1700
Data Index: 7381358 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5035. Min Range: -4.5035
Max Act: 4.3473. Min Act: -0.1700
Data Index: 1572877 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5035. Min Range: -4.5035
Max Act: 4.3160. Min Act: -0.1700
Data Index: 600449 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5035. Min Range: -4.5035
Max Act: 4.3160. Min Act: -0.1700
Data Index: 4540210 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5035. Min Range: -4.5035
Max Act: 4.3160. Min Act: -0.1700
Data Index: 1342840 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5035. Min Range: -4.5035
Max Act: 4.2847. Min Act: -0.1700
Data Index: 7197637 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5035. Min Range: -4.5035
Max Act: 4.2847. Min Act: -0.1700
Data Index: 3374084 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5035. Min Range: -4.5035
Max Act: 4.2847. Min Act: -0.1700
Data Index: 325754 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5035. Min Range: -4.5035
Max Act: 4.2535. Min Act: -0.1700
Data Index: 1149318 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5035. Min Range: -4.5035
Max Act: 4.2222. Min Act: -0.1700
Data Index: 2795704 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5035. Min Range: -4.5035
Max Act: 4.2222. Min Act: -0.1700
Data Index: 3512748 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5035. Min Range: -4.5035
Max Act: 4.2222. Min Act: -0.1700
Data Index: 5738254 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5035. Min Range: -4.5035
Max Act: 4.1910. Min Act: -0.1700
Data Index: 61800 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5035. Min Range: -4.5035
Max Act: 4.1910. Min Act: -0.1700
Data Index: 5503044 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5035. Min Range: -4.5035
Max Act: 4.1910. Min Act: -0.1700
Data Index: 6824204 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5035. Min Range: -4.5035
Max Act: 4.2222. Min Act: -0.1700
Data Index: 1618395 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5035. Min Range: -4.5035
Max Act: 4.1597. Min Act: -0.1700
Data Index: 4266505 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5035. Min Range: -4.5035
Max Act: 4.1597. Min Act: -0.1700
Data Index: 5369836 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19