Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 977 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3630. Min Range: -6.3630
Max Act: 6.3630. Min Act: -0.1700
Data Index: 7844791 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3630. Min Range: -6.3630
Max Act: 6.3317. Min Act: -0.1700
Data Index: 1736285 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3630. Min Range: -6.3630
Max Act: 6.3005. Min Act: -0.1700
Data Index: 3151241 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3630. Min Range: -6.3630
Max Act: 6.2380. Min Act: -0.1700
Data Index: 5027274 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3630. Min Range: -6.3630
Max Act: 6.2067. Min Act: -0.1700
Data Index: 882420 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3630. Min Range: -6.3630
Max Act: 6.1755. Min Act: -0.1700
Data Index: 7388666 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3630. Min Range: -6.3630
Max Act: 6.1755. Min Act: -0.1700
Data Index: 1522935 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3630. Min Range: -6.3630
Max Act: 6.0817. Min Act: -0.1700
Data Index: 7329677 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3630. Min Range: -6.3630
Max Act: 6.1130. Min Act: -0.1700
Data Index: 7648916 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3630. Min Range: -6.3630
Max Act: 6.1130. Min Act: -0.1700
Data Index: 3585631 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3630. Min Range: -6.3630
Max Act: 6.0192. Min Act: -0.1700
Data Index: 2393983 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3630. Min Range: -6.3630
Max Act: 6.0192. Min Act: -0.1700
Data Index: 2248032 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3630. Min Range: -6.3630
Max Act: 5.9880. Min Act: -0.1700
Data Index: 7281177 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3630. Min Range: -6.3630
Max Act: 5.9880. Min Act: -0.1700
Data Index: 7868477 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3630. Min Range: -6.3630
Max Act: 5.9880. Min Act: -0.1700
Data Index: 7606303 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3630. Min Range: -6.3630
Max Act: 5.9567. Min Act: -0.1700
Data Index: 3217598 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3630. Min Range: -6.3630
Max Act: 5.9255. Min Act: -0.1700
Data Index: 4307590 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3630. Min Range: -6.3630
Max Act: 5.9255. Min Act: -0.1700
Data Index: 1603333 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3630. Min Range: -6.3630
Max Act: 5.9255. Min Act: -0.1700
Data Index: 1180323 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3630. Min Range: -6.3630
Max Act: 5.9255. Min Act: -0.1700
Data Index: 5750448 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19