Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1185 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7494. Min Range: -4.7494
Max Act: 4.7494. Min Act: -0.1700
Data Index: 5897951 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7494. Min Range: -4.7494
Max Act: 4.7181. Min Act: -0.1700
Data Index: 5432610 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7494. Min Range: -4.7494
Max Act: 4.5619. Min Act: -0.1700
Data Index: 1755309 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7494. Min Range: -4.7494
Max Act: 4.5619. Min Act: -0.1700
Data Index: 8483439 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7494. Min Range: -4.7494
Max Act: 4.4994. Min Act: -0.1700
Data Index: 4356194 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7494. Min Range: -4.7494
Max Act: 4.4681. Min Act: -0.1700
Data Index: 5917896 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7494. Min Range: -4.7494
Max Act: 4.4369. Min Act: -0.1700
Data Index: 1560419 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7494. Min Range: -4.7494
Max Act: 4.4681. Min Act: -0.1700
Data Index: 7923180 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7494. Min Range: -4.7494
Max Act: 4.4681. Min Act: -0.1700
Data Index: 2219839 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7494. Min Range: -4.7494
Max Act: 4.4681. Min Act: -0.1700
Data Index: 5327024 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7494. Min Range: -4.7494
Max Act: 4.4369. Min Act: -0.1700
Data Index: 2549275 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7494. Min Range: -4.7494
Max Act: 4.4369. Min Act: -0.1700
Data Index: 4126667 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7494. Min Range: -4.7494
Max Act: 4.4056. Min Act: -0.1700
Data Index: 5722302 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7494. Min Range: -4.7494
Max Act: 4.3744. Min Act: -0.1700
Data Index: 6335328 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7494. Min Range: -4.7494
Max Act: 4.3744. Min Act: -0.1700
Data Index: 3644092 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7494. Min Range: -4.7494
Max Act: 4.3431. Min Act: -0.1700
Data Index: 3341858 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7494. Min Range: -4.7494
Max Act: 4.3431. Min Act: -0.1700
Data Index: 8400909 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7494. Min Range: -4.7494
Max Act: 4.3119. Min Act: -0.1700
Data Index: 6772523 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7494. Min Range: -4.7494
Max Act: 4.3431. Min Act: -0.1700
Data Index: 4597781 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7494. Min Range: -4.7494
Max Act: 4.3119. Min Act: -0.1700
Data Index: 3109232 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19