Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3889 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4425. Min Range: -6.4425
Max Act: 6.4113. Min Act: -0.1700
Data Index: 4621847 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4425. Min Range: -6.4425
Max Act: 6.4425. Min Act: -0.1700
Data Index: 4201526 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4425. Min Range: -6.4425
Max Act: 6.4113. Min Act: -0.1700
Data Index: 2194042 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4425. Min Range: -6.4425
Max Act: 6.3488. Min Act: -0.1700
Data Index: 1412488 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4425. Min Range: -6.4425
Max Act: 6.3175. Min Act: -0.1700
Data Index: 4215504 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4425. Min Range: -6.4425
Max Act: 6.3175. Min Act: -0.1700
Data Index: 8087791 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4425. Min Range: -6.4425
Max Act: 6.2550. Min Act: -0.1700
Data Index: 2300580 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4425. Min Range: -6.4425
Max Act: 6.2550. Min Act: -0.1700
Data Index: 4551257 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4425. Min Range: -6.4425
Max Act: 6.2238. Min Act: -0.1700
Data Index: 4206133 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4425. Min Range: -6.4425
Max Act: 6.1925. Min Act: -0.1700
Data Index: 502129 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4425. Min Range: -6.4425
Max Act: 6.1300. Min Act: -0.1700
Data Index: 4887267 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4425. Min Range: -6.4425
Max Act: 6.0988. Min Act: -0.1700
Data Index: 3166091 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4425. Min Range: -6.4425
Max Act: 6.0988. Min Act: -0.1700
Data Index: 27045 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4425. Min Range: -6.4425
Max Act: 6.1300. Min Act: -0.1700
Data Index: 2907610 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4425. Min Range: -6.4425
Max Act: 6.0988. Min Act: -0.1700
Data Index: 216846 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4425. Min Range: -6.4425
Max Act: 6.0363. Min Act: -0.1700
Data Index: 637403 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4425. Min Range: -6.4425
Max Act: 6.0675. Min Act: -0.1700
Data Index: 3349451 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4425. Min Range: -6.4425
Max Act: 6.0363. Min Act: -0.1700
Data Index: 1797630 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4425. Min Range: -6.4425
Max Act: 6.0050. Min Act: -0.1700
Data Index: 3179274 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4425. Min Range: -6.4425
Max Act: 6.0050. Min Act: -0.1700
Data Index: 2995166 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19