Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2504 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3407. Min Range: -5.3407
Max Act: 5.3407. Min Act: -0.1700
Data Index: 2051 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3407. Min Range: -5.3407
Max Act: 5.1220. Min Act: -0.1700
Data Index: 4759393 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3407. Min Range: -5.3407
Max Act: 5.1220. Min Act: -0.1700
Data Index: 8749270 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3407. Min Range: -5.3407
Max Act: 5.0595. Min Act: -0.1700
Data Index: 3793727 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3407. Min Range: -5.3407
Max Act: 5.0282. Min Act: -0.1700
Data Index: 2996904 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3407. Min Range: -5.3407
Max Act: 5.0595. Min Act: -0.1699
Data Index: 3392238 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3407. Min Range: -5.3407
Max Act: 5.0595. Min Act: -0.1700
Data Index: 4928682 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3407. Min Range: -5.3407
Max Act: 5.0282. Min Act: -0.1700
Data Index: 5886272 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3407. Min Range: -5.3407
Max Act: 5.0282. Min Act: -0.1700
Data Index: 790676 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3407. Min Range: -5.3407
Max Act: 5.0282. Min Act: -0.1700
Data Index: 3757831 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3407. Min Range: -5.3407
Max Act: 4.9657. Min Act: -0.1700
Data Index: 2202407 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3407. Min Range: -5.3407
Max Act: 4.9970. Min Act: -0.1700
Data Index: 875713 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3407. Min Range: -5.3407
Max Act: 4.9970. Min Act: -0.1700
Data Index: 5449234 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3407. Min Range: -5.3407
Max Act: 4.9657. Min Act: -0.1700
Data Index: 212934 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3407. Min Range: -5.3407
Max Act: 4.9657. Min Act: -0.1700
Data Index: 2587622 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3407. Min Range: -5.3407
Max Act: 4.9657. Min Act: -0.1700
Data Index: 2927479 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3407. Min Range: -5.3407
Max Act: 4.9345. Min Act: -0.1699
Data Index: 5273331 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3407. Min Range: -5.3407
Max Act: 4.9657. Min Act: -0.1700
Data Index: 3775914 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3407. Min Range: -5.3407
Max Act: 4.9345. Min Act: -0.1700
Data Index: 982141 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3407. Min Range: -5.3407
Max Act: 4.9032. Min Act: -0.1700
Data Index: 3925315 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19