Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 683 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1441. Min Range: -8.1441
Max Act: 8.1441. Min Act: -0.1700
Data Index: 7901940 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1441. Min Range: -8.1441
Max Act: 8.0816. Min Act: -0.1700
Data Index: 724301 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1441. Min Range: -8.1441
Max Act: 8.0816. Min Act: -0.1700
Data Index: 5383720 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1441. Min Range: -8.1441
Max Act: 7.9566. Min Act: -0.1700
Data Index: 2385491 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1441. Min Range: -8.1441
Max Act: 7.9878. Min Act: -0.1700
Data Index: 5383714 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1441. Min Range: -8.1441
Max Act: 7.9253. Min Act: -0.1700
Data Index: 7876032 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1441. Min Range: -8.1441
Max Act: 7.9253. Min Act: -0.1700
Data Index: 4653597 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1441. Min Range: -8.1441
Max Act: 7.8628. Min Act: -0.1700
Data Index: 6353811 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1441. Min Range: -8.1441
Max Act: 7.8628. Min Act: -0.1700
Data Index: 7395036 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1441. Min Range: -8.1441
Max Act: 7.8316. Min Act: -0.1700
Data Index: 7696087 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1441. Min Range: -8.1441
Max Act: 7.8316. Min Act: -0.1700
Data Index: 914489 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1441. Min Range: -8.1441
Max Act: 7.8316. Min Act: -0.1700
Data Index: 4232912 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1441. Min Range: -8.1441
Max Act: 7.8003. Min Act: -0.1700
Data Index: 1103892 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1441. Min Range: -8.1441
Max Act: 7.7691. Min Act: -0.1700
Data Index: 6125811 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1441. Min Range: -8.1441
Max Act: 7.7066. Min Act: -0.1700
Data Index: 302191 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1441. Min Range: -8.1441
Max Act: 7.7378. Min Act: -0.1700
Data Index: 8469665 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1441. Min Range: -8.1441
Max Act: 7.7378. Min Act: -0.1700
Data Index: 501557 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1441. Min Range: -8.1441
Max Act: 7.7378. Min Act: -0.1700
Data Index: 4269178 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1441. Min Range: -8.1441
Max Act: 7.7691. Min Act: -0.1700
Data Index: 3923088 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1441. Min Range: -8.1441
Max Act: 7.7378. Min Act: -0.1700
Data Index: 2040593 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19