Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3539 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7563. Min Range: -6.7563
Max Act: 6.7563. Min Act: -0.1700
Data Index: 2941810 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7563. Min Range: -6.7563
Max Act: 6.6000. Min Act: -0.1700
Data Index: 486092 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7563. Min Range: -6.7563
Max Act: 6.4438. Min Act: -0.1700
Data Index: 7844246 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7563. Min Range: -6.7563
Max Act: 6.3813. Min Act: -0.1700
Data Index: 4250118 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7563. Min Range: -6.7563
Max Act: 6.3500. Min Act: -0.1700
Data Index: 511955 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7563. Min Range: -6.7563
Max Act: 6.3188. Min Act: -0.1700
Data Index: 6401244 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7563. Min Range: -6.7563
Max Act: 6.3188. Min Act: -0.1700
Data Index: 8286788 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7563. Min Range: -6.7563
Max Act: 6.3188. Min Act: -0.1700
Data Index: 1915021 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7563. Min Range: -6.7563
Max Act: 6.2875. Min Act: -0.1700
Data Index: 6398675 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7563. Min Range: -6.7563
Max Act: 6.2563. Min Act: -0.1700
Data Index: 1270676 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7563. Min Range: -6.7563
Max Act: 6.2250. Min Act: -0.1700
Data Index: 6074549 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7563. Min Range: -6.7563
Max Act: 6.2563. Min Act: -0.1700
Data Index: 7981135 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7563. Min Range: -6.7563
Max Act: 6.2563. Min Act: -0.1700
Data Index: 4508589 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7563. Min Range: -6.7563
Max Act: 6.2250. Min Act: -0.1700
Data Index: 7565110 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7563. Min Range: -6.7563
Max Act: 6.1938. Min Act: -0.1700
Data Index: 6870495 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7563. Min Range: -6.7563
Max Act: 6.1625. Min Act: -0.1700
Data Index: 8213891 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7563. Min Range: -6.7563
Max Act: 6.1625. Min Act: -0.1700
Data Index: 1821985 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7563. Min Range: -6.7563
Max Act: 6.1000. Min Act: -0.1700
Data Index: 573833 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7563. Min Range: -6.7563
Max Act: 6.1313. Min Act: -0.1700
Data Index: 1140601 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7563. Min Range: -6.7563
Max Act: 6.1000. Min Act: -0.1700
Data Index: 5559865 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19