Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2038 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9248. Min Range: -3.9248
Max Act: 3.9248. Min Act: -0.1700
Data Index: 4298581 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9248. Min Range: -3.9248
Max Act: 3.8935. Min Act: -0.1700
Data Index: 1224358 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9248. Min Range: -3.9248
Max Act: 3.7997. Min Act: -0.1700
Data Index: 7222031 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9248. Min Range: -3.9248
Max Act: 3.7528. Min Act: -0.1700
Data Index: 1412070 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9248. Min Range: -3.9248
Max Act: 3.7059. Min Act: -0.1700
Data Index: 6287731 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9248. Min Range: -3.9248
Max Act: 3.7059. Min Act: -0.1700
Data Index: 3353826 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9248. Min Range: -3.9248
Max Act: 3.6902. Min Act: -0.1700
Data Index: 7388359 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9248. Min Range: -3.9248
Max Act: 3.6589. Min Act: -0.1700
Data Index: 2875622 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9248. Min Range: -3.9248
Max Act: 3.6433. Min Act: -0.1700
Data Index: 6314904 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9248. Min Range: -3.9248
Max Act: 3.6433. Min Act: -0.1700
Data Index: 8328639 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9248. Min Range: -3.9248
Max Act: 3.6433. Min Act: -0.1700
Data Index: 4525723 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9248. Min Range: -3.9248
Max Act: 3.6276. Min Act: -0.1700
Data Index: 382463 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9248. Min Range: -3.9248
Max Act: 3.6120. Min Act: -0.1700
Data Index: 7661983 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9248. Min Range: -3.9248
Max Act: 3.6120. Min Act: -0.1700
Data Index: 5586345 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9248. Min Range: -3.9248
Max Act: 3.5963. Min Act: -0.1700
Data Index: 5362068 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9248. Min Range: -3.9248
Max Act: 3.5963. Min Act: -0.1700
Data Index: 3173866 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9248. Min Range: -3.9248
Max Act: 3.5963. Min Act: -0.1700
Data Index: 7516805 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9248. Min Range: -3.9248
Max Act: 3.5650. Min Act: -0.1700
Data Index: 8658131 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9248. Min Range: -3.9248
Max Act: 3.5494. Min Act: -0.1700
Data Index: 443687 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9248. Min Range: -3.9248
Max Act: 3.5494. Min Act: -0.1700
Data Index: 4368208 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19