Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2689 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3218. Min Range: -8.3218
Max Act: 8.3218. Min Act: -0.1700
Data Index: 4373429 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3218. Min Range: -8.3218
Max Act: 8.1343. Min Act: -0.1700
Data Index: 6412003 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3218. Min Range: -8.3218
Max Act: 7.9468. Min Act: -0.1700
Data Index: 135056 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3218. Min Range: -8.3218
Max Act: 7.8843. Min Act: -0.1700
Data Index: 1651454 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3218. Min Range: -8.3218
Max Act: 7.8843. Min Act: -0.1700
Data Index: 5780562 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3218. Min Range: -8.3218
Max Act: 7.8218. Min Act: -0.1700
Data Index: 4867147 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3218. Min Range: -8.3218
Max Act: 7.7593. Min Act: -0.1700
Data Index: 7352747 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3218. Min Range: -8.3218
Max Act: 7.7593. Min Act: -0.1700
Data Index: 2997856 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3218. Min Range: -8.3218
Max Act: 7.6343. Min Act: -0.1700
Data Index: 2963945 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3218. Min Range: -8.3218
Max Act: 7.6968. Min Act: -0.1700
Data Index: 5661863 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3218. Min Range: -8.3218
Max Act: 7.6968. Min Act: -0.1700
Data Index: 4352764 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3218. Min Range: -8.3218
Max Act: 7.6343. Min Act: -0.1700
Data Index: 4967065 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3218. Min Range: -8.3218
Max Act: 7.6343. Min Act: -0.1700
Data Index: 195855 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3218. Min Range: -8.3218
Max Act: 7.6343. Min Act: -0.1700
Data Index: 6592681 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3218. Min Range: -8.3218
Max Act: 7.6343. Min Act: -0.1700
Data Index: 4097601 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3218. Min Range: -8.3218
Max Act: 7.5718. Min Act: -0.1700
Data Index: 2452485 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3218. Min Range: -8.3218
Max Act: 7.5718. Min Act: -0.1700
Data Index: 6786572 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3218. Min Range: -8.3218
Max Act: 7.5718. Min Act: -0.1700
Data Index: 4385692 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3218. Min Range: -8.3218
Max Act: 7.5718. Min Act: -0.1700
Data Index: 4439370 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3218. Min Range: -8.3218
Max Act: 7.5718. Min Act: -0.1700
Data Index: 360160 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19