Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1273 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1243. Min Range: -8.1243
Max Act: 8.0618. Min Act: -0.1700
Data Index: 552424 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1243. Min Range: -8.1243
Max Act: 8.1243. Min Act: -0.1700
Data Index: 7774592 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1243. Min Range: -8.1243
Max Act: 7.7493. Min Act: -0.1700
Data Index: 8815405 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1243. Min Range: -8.1243
Max Act: 7.6243. Min Act: -0.1700
Data Index: 3473852 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1243. Min Range: -8.1243
Max Act: 7.6243. Min Act: -0.1700
Data Index: 7728790 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1243. Min Range: -8.1243
Max Act: 7.4993. Min Act: -0.1700
Data Index: 6919555 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1243. Min Range: -8.1243
Max Act: 7.4680. Min Act: -0.1700
Data Index: 1962486 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1243. Min Range: -8.1243
Max Act: 7.4680. Min Act: -0.1700
Data Index: 7539579 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1243. Min Range: -8.1243
Max Act: 7.4368. Min Act: -0.1700
Data Index: 1057584 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1243. Min Range: -8.1243
Max Act: 7.3743. Min Act: -0.1700
Data Index: 7047981 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1243. Min Range: -8.1243
Max Act: 7.3743. Min Act: -0.1700
Data Index: 8408953 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1243. Min Range: -8.1243
Max Act: 7.3430. Min Act: -0.1700
Data Index: 4740701 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1243. Min Range: -8.1243
Max Act: 7.3430. Min Act: -0.1700
Data Index: 4226903 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1243. Min Range: -8.1243
Max Act: 7.3118. Min Act: -0.1700
Data Index: 8376416 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1243. Min Range: -8.1243
Max Act: 7.3118. Min Act: -0.1700
Data Index: 1186854 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1243. Min Range: -8.1243
Max Act: 7.2805. Min Act: -0.1700
Data Index: 6015555 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1243. Min Range: -8.1243
Max Act: 7.2805. Min Act: -0.1700
Data Index: 2571648 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1243. Min Range: -8.1243
Max Act: 7.2805. Min Act: -0.1700
Data Index: 3318487 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1243. Min Range: -8.1243
Max Act: 7.2805. Min Act: -0.1700
Data Index: 652018 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1243. Min Range: -8.1243
Max Act: 7.2493. Min Act: -0.1700
Data Index: 3002598 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #19