Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4387 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8298. Min Range: -7.8298
Max Act: 7.8298. Min Act: -0.1700
Data Index: 4789741 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8298. Min Range: -7.8298
Max Act: 7.7048. Min Act: -0.1700
Data Index: 1442323 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8298. Min Range: -7.8298
Max Act: 7.5485. Min Act: -0.1700
Data Index: 5906394 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8298. Min Range: -7.8298
Max Act: 7.4860. Min Act: -0.1700
Data Index: 8168082 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8298. Min Range: -7.8298
Max Act: 7.4235. Min Act: -0.1700
Data Index: 4589078 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8298. Min Range: -7.8298
Max Act: 7.3298. Min Act: -0.1700
Data Index: 4729999 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8298. Min Range: -7.8298
Max Act: 7.2360. Min Act: -0.1700
Data Index: 2107540 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8298. Min Range: -7.8298
Max Act: 7.2360. Min Act: -0.1700
Data Index: 7547611 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8298. Min Range: -7.8298
Max Act: 7.2048. Min Act: -0.1700
Data Index: 6057882 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8298. Min Range: -7.8298
Max Act: 7.2048. Min Act: -0.1700
Data Index: 5765734 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8298. Min Range: -7.8298
Max Act: 7.1735. Min Act: -0.1700
Data Index: 1134290 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8298. Min Range: -7.8298
Max Act: 7.1110. Min Act: -0.1700
Data Index: 233681 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8298. Min Range: -7.8298
Max Act: 7.1110. Min Act: -0.1700
Data Index: 3887034 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8298. Min Range: -7.8298
Max Act: 7.0173. Min Act: -0.1700
Data Index: 8385106 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8298. Min Range: -7.8298
Max Act: 6.9548. Min Act: -0.1700
Data Index: 4602830 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8298. Min Range: -7.8298
Max Act: 6.9548. Min Act: -0.1700
Data Index: 1077618 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8298. Min Range: -7.8298
Max Act: 6.9860. Min Act: -0.1700
Data Index: 3124075 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8298. Min Range: -7.8298
Max Act: 6.9860. Min Act: -0.1700
Data Index: 374447 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8298. Min Range: -7.8298
Max Act: 6.9860. Min Act: -0.1700
Data Index: 1896021 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8298. Min Range: -7.8298
Max Act: 6.9548. Min Act: -0.1700
Data Index: 6347530 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #19