Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1985 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2326. Min Range: -5.2326
Max Act: 5.2326. Min Act: -0.1700
Data Index: 5718493 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2326. Min Range: -5.2326
Max Act: 5.1701. Min Act: -0.1700
Data Index: 626223 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2326. Min Range: -5.2326
Max Act: 5.1388. Min Act: -0.1700
Data Index: 878386 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2326. Min Range: -5.2326
Max Act: 5.1388. Min Act: -0.1700
Data Index: 6145192 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2326. Min Range: -5.2326
Max Act: 5.1388. Min Act: -0.1700
Data Index: 5114900 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2326. Min Range: -5.2326
Max Act: 5.1076. Min Act: -0.1700
Data Index: 2479127 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2326. Min Range: -5.2326
Max Act: 5.0763. Min Act: -0.1700
Data Index: 7893268 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2326. Min Range: -5.2326
Max Act: 5.0763. Min Act: -0.1700
Data Index: 5400347 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2326. Min Range: -5.2326
Max Act: 5.0763. Min Act: -0.1700
Data Index: 1181077 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2326. Min Range: -5.2326
Max Act: 5.0451. Min Act: -0.1700
Data Index: 694261 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2326. Min Range: -5.2326
Max Act: 5.0451. Min Act: -0.1700
Data Index: 3209297 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2326. Min Range: -5.2326
Max Act: 5.0138. Min Act: -0.1700
Data Index: 8745631 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2326. Min Range: -5.2326
Max Act: 5.0138. Min Act: -0.1700
Data Index: 3577204 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2326. Min Range: -5.2326
Max Act: 4.9825. Min Act: -0.1700
Data Index: 5640933 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2326. Min Range: -5.2326
Max Act: 5.0138. Min Act: -0.1700
Data Index: 7665667 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2326. Min Range: -5.2326
Max Act: 4.9825. Min Act: -0.1700
Data Index: 6435948 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2326. Min Range: -5.2326
Max Act: 5.0138. Min Act: -0.1700
Data Index: 2990537 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2326. Min Range: -5.2326
Max Act: 4.9825. Min Act: -0.1700
Data Index: 5135088 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2326. Min Range: -5.2326
Max Act: 4.9825. Min Act: -0.1700
Data Index: 4379617 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2326. Min Range: -5.2326
Max Act: 4.9825. Min Act: -0.1700
Data Index: 6382685 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19