Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2874 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3854. Min Range: -9.3854
Max Act: 9.3854. Min Act: -0.1700
Data Index: 387885 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3854. Min Range: -9.3854
Max Act: 9.2604. Min Act: -0.1700
Data Index: 6439431 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3854. Min Range: -9.3854
Max Act: 9.0104. Min Act: -0.1700
Data Index: 2690348 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3854. Min Range: -9.3854
Max Act: 8.8229. Min Act: -0.1700
Data Index: 2746073 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3854. Min Range: -9.3854
Max Act: 8.8229. Min Act: -0.1700
Data Index: 4507700 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3854. Min Range: -9.3854
Max Act: 8.8229. Min Act: -0.1700
Data Index: 6974301 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3854. Min Range: -9.3854
Max Act: 8.7604. Min Act: -0.1700
Data Index: 8502545 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3854. Min Range: -9.3854
Max Act: 8.8229. Min Act: -0.1700
Data Index: 7602801 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3854. Min Range: -9.3854
Max Act: 8.8854. Min Act: -0.1700
Data Index: 6275101 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3854. Min Range: -9.3854
Max Act: 8.7604. Min Act: -0.1700
Data Index: 2606410 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3854. Min Range: -9.3854
Max Act: 8.7604. Min Act: -0.1700
Data Index: 2219047 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3854. Min Range: -9.3854
Max Act: 8.7604. Min Act: -0.1700
Data Index: 658290 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3854. Min Range: -9.3854
Max Act: 8.6979. Min Act: -0.1700
Data Index: 4916346 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3854. Min Range: -9.3854
Max Act: 8.6979. Min Act: -0.1700
Data Index: 7544305 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3854. Min Range: -9.3854
Max Act: 8.6979. Min Act: -0.1700
Data Index: 3610655 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3854. Min Range: -9.3854
Max Act: 8.6354. Min Act: -0.1700
Data Index: 4284287 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3854. Min Range: -9.3854
Max Act: 8.6979. Min Act: -0.1700
Data Index: 3832611 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3854. Min Range: -9.3854
Max Act: 8.6354. Min Act: -0.1700
Data Index: 3693701 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3854. Min Range: -9.3854
Max Act: 8.6354. Min Act: -0.1700
Data Index: 5766121 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3854. Min Range: -9.3854
Max Act: 8.5729. Min Act: -0.1700
Data Index: 5679630 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19