Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5113 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1639. Min Range: -8.1639
Max Act: 8.1639. Min Act: -0.1700
Data Index: 11974 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1639. Min Range: -8.1639
Max Act: 7.9139. Min Act: -0.1700
Data Index: 586900 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1639. Min Range: -8.1639
Max Act: 7.8202. Min Act: -0.1700
Data Index: 51984 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1639. Min Range: -8.1639
Max Act: 7.7889. Min Act: -0.1700
Data Index: 1429225 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1639. Min Range: -8.1639
Max Act: 7.7264. Min Act: -0.1700
Data Index: 4359193 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1639. Min Range: -8.1639
Max Act: 7.7264. Min Act: -0.1700
Data Index: 5338242 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1639. Min Range: -8.1639
Max Act: 7.7264. Min Act: -0.1700
Data Index: 8739984 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1639. Min Range: -8.1639
Max Act: 7.6952. Min Act: -0.1700
Data Index: 7503939 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1639. Min Range: -8.1639
Max Act: 7.6952. Min Act: -0.1700
Data Index: 3209934 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1639. Min Range: -8.1639
Max Act: 7.6639. Min Act: -0.1700
Data Index: 5318586 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1639. Min Range: -8.1639
Max Act: 7.6327. Min Act: -0.1700
Data Index: 6172538 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1639. Min Range: -8.1639
Max Act: 7.5702. Min Act: -0.1700
Data Index: 2756483 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1639. Min Range: -8.1639
Max Act: 7.5702. Min Act: -0.1700
Data Index: 5835079 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1639. Min Range: -8.1639
Max Act: 7.4764. Min Act: -0.1699
Data Index: 2377814 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1639. Min Range: -8.1639
Max Act: 7.5389. Min Act: -0.1700
Data Index: 4768480 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1639. Min Range: -8.1639
Max Act: 7.5077. Min Act: -0.1700
Data Index: 5100639 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1639. Min Range: -8.1639
Max Act: 7.5389. Min Act: -0.1700
Data Index: 4606573 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1639. Min Range: -8.1639
Max Act: 7.5077. Min Act: -0.1700
Data Index: 4542851 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1639. Min Range: -8.1639
Max Act: 7.5389. Min Act: -0.1700
Data Index: 2624502 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1639. Min Range: -8.1639
Max Act: 7.5389. Min Act: -0.1700
Data Index: 2695187 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19