Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3960 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3371. Min Range: -5.3371
Max Act: 5.3371. Min Act: -0.1700
Data Index: 2020670 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3371. Min Range: -5.3371
Max Act: 5.3371. Min Act: -0.1700
Data Index: 5819635 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3371. Min Range: -5.3371
Max Act: 5.2433. Min Act: -0.1700
Data Index: 1453156 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3371. Min Range: -5.3371
Max Act: 5.2433. Min Act: -0.1700
Data Index: 3698142 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3371. Min Range: -5.3371
Max Act: 5.1808. Min Act: -0.1700
Data Index: 3595000 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3371. Min Range: -5.3371
Max Act: 5.1496. Min Act: -0.1700
Data Index: 8414585 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3371. Min Range: -5.3371
Max Act: 5.1183. Min Act: -0.1700
Data Index: 1600232 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3371. Min Range: -5.3371
Max Act: 5.1183. Min Act: -0.1700
Data Index: 7446473 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3371. Min Range: -5.3371
Max Act: 5.1183. Min Act: -0.1700
Data Index: 7324762 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3371. Min Range: -5.3371
Max Act: 5.0871. Min Act: -0.1700
Data Index: 7802874 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3371. Min Range: -5.3371
Max Act: 5.0558. Min Act: -0.1700
Data Index: 7259033 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3371. Min Range: -5.3371
Max Act: 5.0558. Min Act: -0.1700
Data Index: 4516523 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3371. Min Range: -5.3371
Max Act: 5.0246. Min Act: -0.1700
Data Index: 249737 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3371. Min Range: -5.3371
Max Act: 5.0246. Min Act: -0.1700
Data Index: 1058529 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3371. Min Range: -5.3371
Max Act: 5.0558. Min Act: -0.1700
Data Index: 5783791 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3371. Min Range: -5.3371
Max Act: 5.0558. Min Act: -0.1700
Data Index: 4647739 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3371. Min Range: -5.3371
Max Act: 5.0246. Min Act: -0.1700
Data Index: 5164859 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3371. Min Range: -5.3371
Max Act: 5.0246. Min Act: -0.1700
Data Index: 4017701 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3371. Min Range: -5.3371
Max Act: 5.0246. Min Act: -0.1700
Data Index: 4214775 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3371. Min Range: -5.3371
Max Act: 5.0246. Min Act: -0.1700
Data Index: 3145724 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19