Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4436 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.4539. Min Act: -0.1700
Data Index: 5162832 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.4539. Min Act: -0.1700
Data Index: 3948322 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.4227. Min Act: -0.1700
Data Index: 6869956 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.4227. Min Act: -0.1700
Data Index: 5315911 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.3602. Min Act: -0.1700
Data Index: 7228354 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.3289. Min Act: -0.1700
Data Index: 1419526 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.3289. Min Act: -0.1700
Data Index: 4166317 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.2977. Min Act: -0.1700
Data Index: 4280275 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.2664. Min Act: -0.1700
Data Index: 2536078 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.2352. Min Act: -0.1700
Data Index: 8120446 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.2352. Min Act: -0.1700
Data Index: 7773512 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.2352. Min Act: -0.1700
Data Index: 3524245 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.2352. Min Act: -0.1700
Data Index: 7934094 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.2039. Min Act: -0.1700
Data Index: 3893431 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.2039. Min Act: -0.1700
Data Index: 3949185 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.1414. Min Act: -0.1700
Data Index: 2446638 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.1414. Min Act: -0.1700
Data Index: 6632661 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.1102. Min Act: -0.1700
Data Index: 6371565 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.1414. Min Act: -0.1700
Data Index: 6540286 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.1102. Min Act: -0.1700
Data Index: 4338955 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19