Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 529 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0120. Min Range: -7.0120
Max Act: 7.0120. Min Act: -0.1700
Data Index: 5169049 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0120. Min Range: -7.0120
Max Act: 7.0120. Min Act: -0.1700
Data Index: 982306 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0120. Min Range: -7.0120
Max Act: 6.9495. Min Act: -0.1700
Data Index: 5169038 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0120. Min Range: -7.0120
Max Act: 6.9808. Min Act: -0.1700
Data Index: 2299672 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0120. Min Range: -7.0120
Max Act: 6.9495. Min Act: -0.1700
Data Index: 7736654 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0120. Min Range: -7.0120
Max Act: 6.8870. Min Act: -0.1700
Data Index: 3758954 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0120. Min Range: -7.0120
Max Act: 6.8558. Min Act: -0.1700
Data Index: 8125273 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0120. Min Range: -7.0120
Max Act: 6.6683. Min Act: -0.1700
Data Index: 6946972 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0120. Min Range: -7.0120
Max Act: 6.6370. Min Act: -0.1700
Data Index: 772465 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0120. Min Range: -7.0120
Max Act: 6.6370. Min Act: -0.1700
Data Index: 3514498 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0120. Min Range: -7.0120
Max Act: 6.5745. Min Act: -0.1700
Data Index: 2026922 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0120. Min Range: -7.0120
Max Act: 6.5433. Min Act: -0.1700
Data Index: 3976729 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0120. Min Range: -7.0120
Max Act: 6.5120. Min Act: -0.1700
Data Index: 6938347 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0120. Min Range: -7.0120
Max Act: 6.5120. Min Act: -0.1700
Data Index: 3763131 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0120. Min Range: -7.0120
Max Act: 6.5120. Min Act: -0.1700
Data Index: 2299671 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0120. Min Range: -7.0120
Max Act: 6.4495. Min Act: -0.1700
Data Index: 1281513 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0120. Min Range: -7.0120
Max Act: 6.4495. Min Act: -0.1700
Data Index: 7132696 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0120. Min Range: -7.0120
Max Act: 6.4495. Min Act: -0.1700
Data Index: 5169036 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0120. Min Range: -7.0120
Max Act: 6.4183. Min Act: -0.1700
Data Index: 2945403 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0120. Min Range: -7.0120
Max Act: 6.4183. Min Act: -0.1700
Data Index: 4522557 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19