Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3692 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4979. Min Range: -5.4979
Max Act: 5.4979. Min Act: -0.1700
Data Index: 5418344 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4979. Min Range: -5.4979
Max Act: 5.4667. Min Act: -0.1700
Data Index: 2538847 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4979. Min Range: -5.4979
Max Act: 5.4354. Min Act: -0.1700
Data Index: 1265696 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4979. Min Range: -5.4979
Max Act: 5.4354. Min Act: -0.1700
Data Index: 6761261 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4979. Min Range: -5.4979
Max Act: 5.4354. Min Act: -0.1700
Data Index: 5884532 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4979. Min Range: -5.4979
Max Act: 5.4042. Min Act: -0.1700
Data Index: 399356 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4979. Min Range: -5.4979
Max Act: 5.3729. Min Act: -0.1700
Data Index: 4440243 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4979. Min Range: -5.4979
Max Act: 5.3417. Min Act: -0.1700
Data Index: 2507405 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4979. Min Range: -5.4979
Max Act: 5.3417. Min Act: -0.1700
Data Index: 3116769 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4979. Min Range: -5.4979
Max Act: 5.3104. Min Act: -0.1700
Data Index: 979697 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4979. Min Range: -5.4979
Max Act: 5.2479. Min Act: -0.1700
Data Index: 7777575 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4979. Min Range: -5.4979
Max Act: 5.1854. Min Act: -0.1700
Data Index: 7978328 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4979. Min Range: -5.4979
Max Act: 5.1854. Min Act: -0.1700
Data Index: 3703090 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4979. Min Range: -5.4979
Max Act: 5.1854. Min Act: -0.1700
Data Index: 7458555 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4979. Min Range: -5.4979
Max Act: 5.1542. Min Act: -0.1700
Data Index: 8480855 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4979. Min Range: -5.4979
Max Act: 5.1229. Min Act: -0.1700
Data Index: 6284035 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4979. Min Range: -5.4979
Max Act: 5.1542. Min Act: -0.1700
Data Index: 3142729 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4979. Min Range: -5.4979
Max Act: 5.1229. Min Act: -0.1700
Data Index: 556109 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4979. Min Range: -5.4979
Max Act: 5.1229. Min Act: -0.1700
Data Index: 3277530 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4979. Min Range: -5.4979
Max Act: 5.1229. Min Act: -0.1700
Data Index: 2459770 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19