Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7771. Min Range: -6.7771
Max Act: 6.7771. Min Act: -0.1700
Data Index: 2272515 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7771. Min Range: -6.7771
Max Act: 6.6834. Min Act: -0.1700
Data Index: 8826909 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7771. Min Range: -6.7771
Max Act: 6.6209. Min Act: -0.1700
Data Index: 2339565 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7771. Min Range: -6.7771
Max Act: 6.6209. Min Act: -0.1700
Data Index: 5691482 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7771. Min Range: -6.7771
Max Act: 6.5896. Min Act: -0.1700
Data Index: 2705838 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7771. Min Range: -6.7771
Max Act: 6.5896. Min Act: -0.1700
Data Index: 489125 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7771. Min Range: -6.7771
Max Act: 6.5896. Min Act: -0.1700
Data Index: 7184921 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7771. Min Range: -6.7771
Max Act: 6.5584. Min Act: -0.1700
Data Index: 8658721 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7771. Min Range: -6.7771
Max Act: 6.5271. Min Act: -0.1700
Data Index: 4411184 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7771. Min Range: -6.7771
Max Act: 6.5271. Min Act: -0.1700
Data Index: 7780862 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7771. Min Range: -6.7771
Max Act: 6.4959. Min Act: -0.1700
Data Index: 3221794 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7771. Min Range: -6.7771
Max Act: 6.4959. Min Act: -0.1700
Data Index: 3408647 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7771. Min Range: -6.7771
Max Act: 6.4959. Min Act: -0.1700
Data Index: 2009873 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7771. Min Range: -6.7771
Max Act: 6.4959. Min Act: -0.1700
Data Index: 8792519 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7771. Min Range: -6.7771
Max Act: 6.4646. Min Act: -0.1700
Data Index: 1450896 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7771. Min Range: -6.7771
Max Act: 6.4334. Min Act: -0.1700
Data Index: 4625314 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7771. Min Range: -6.7771
Max Act: 6.4334. Min Act: -0.1700
Data Index: 4907716 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7771. Min Range: -6.7771
Max Act: 6.4334. Min Act: -0.1700
Data Index: 4167045 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7771. Min Range: -6.7771
Max Act: 6.4334. Min Act: -0.1700
Data Index: 3954079 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7771. Min Range: -6.7771
Max Act: 6.4021. Min Act: -0.1700
Data Index: 3129596 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19