Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5791 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9754. Min Range: -3.9754
Max Act: 3.9754. Min Act: -0.1700
Data Index: 885992 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9754. Min Range: -3.9754
Max Act: 3.9754. Min Act: -0.1700
Data Index: 7877302 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9754. Min Range: -3.9754
Max Act: 3.9441. Min Act: -0.1700
Data Index: 2646537 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9754. Min Range: -3.9754
Max Act: 3.8816. Min Act: -0.1700
Data Index: 6168934 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9754. Min Range: -3.9754
Max Act: 3.8816. Min Act: -0.1700
Data Index: 3683909 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9754. Min Range: -3.9754
Max Act: 3.8191. Min Act: -0.1700
Data Index: 1704669 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9754. Min Range: -3.9754
Max Act: 3.8034. Min Act: -0.1700
Data Index: 258023 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9754. Min Range: -3.9754
Max Act: 3.8034. Min Act: -0.1700
Data Index: 7926344 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9754. Min Range: -3.9754
Max Act: 3.8034. Min Act: -0.1700
Data Index: 1355616 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9754. Min Range: -3.9754
Max Act: 3.7878. Min Act: -0.1700
Data Index: 2997020 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9754. Min Range: -3.9754
Max Act: 3.7878. Min Act: -0.1700
Data Index: 7336996 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9754. Min Range: -3.9754
Max Act: 3.7878. Min Act: -0.1700
Data Index: 6936649 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9754. Min Range: -3.9754
Max Act: 3.7722. Min Act: -0.1700
Data Index: 6316069 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9754. Min Range: -3.9754
Max Act: 3.7878. Min Act: -0.1700
Data Index: 3344703 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9754. Min Range: -3.9754
Max Act: 3.7722. Min Act: -0.1700
Data Index: 5784436 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9754. Min Range: -3.9754
Max Act: 3.7565. Min Act: -0.1700
Data Index: 4745028 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9754. Min Range: -3.9754
Max Act: 3.7722. Min Act: -0.1700
Data Index: 442082 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9754. Min Range: -3.9754
Max Act: 3.7409. Min Act: -0.1700
Data Index: 7953730 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9754. Min Range: -3.9754
Max Act: 3.7096. Min Act: -0.1700
Data Index: 4776556 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9754. Min Range: -3.9754
Max Act: 3.7252. Min Act: -0.1700
Data Index: 4370561 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19