Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4826 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2492. Min Range: -5.2492
Max Act: 5.2492. Min Act: -0.1700
Data Index: 6683345 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2492. Min Range: -5.2492
Max Act: 5.1555. Min Act: -0.1700
Data Index: 4931629 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2492. Min Range: -5.2492
Max Act: 5.1242. Min Act: -0.1700
Data Index: 6321694 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2492. Min Range: -5.2492
Max Act: 5.0617. Min Act: -0.1700
Data Index: 376567 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.9992. Min Act: -0.1700
Data Index: 7248707 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.9992. Min Act: -0.1700
Data Index: 7112794 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.9680. Min Act: -0.1700
Data Index: 6683327 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.9367. Min Act: -0.1700
Data Index: 4075665 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.9055. Min Act: -0.1700
Data Index: 6683328 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.9055. Min Act: -0.1700
Data Index: 2745752 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.9055. Min Act: -0.1700
Data Index: 2416941 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.8742. Min Act: -0.1700
Data Index: 5223214 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.9055. Min Act: -0.1700
Data Index: 4075676 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.8742. Min Act: -0.1700
Data Index: 386112 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.8430. Min Act: -0.1700
Data Index: 3788656 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.8430. Min Act: -0.1700
Data Index: 6683332 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.8430. Min Act: -0.1700
Data Index: 6683347 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.8117. Min Act: -0.1700
Data Index: 6946082 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.8430. Min Act: -0.1700
Data Index: 3627043 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.8117. Min Act: -0.1700
Data Index: 4149374 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19