Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1321 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5236. Min Range: -6.5236
Max Act: 6.5236. Min Act: -0.1700
Data Index: 2622611 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5236. Min Range: -6.5236
Max Act: 6.2423. Min Act: -0.1700
Data Index: 7803710 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5236. Min Range: -6.5236
Max Act: 6.2423. Min Act: -0.1700
Data Index: 5332189 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5236. Min Range: -6.5236
Max Act: 6.2423. Min Act: -0.1700
Data Index: 2911999 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5236. Min Range: -6.5236
Max Act: 6.2423. Min Act: -0.1700
Data Index: 6048290 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5236. Min Range: -6.5236
Max Act: 6.1486. Min Act: -0.1700
Data Index: 2922182 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5236. Min Range: -6.5236
Max Act: 6.0861. Min Act: -0.1700
Data Index: 8355175 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5236. Min Range: -6.5236
Max Act: 6.0236. Min Act: -0.1700
Data Index: 687156 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5236. Min Range: -6.5236
Max Act: 5.9923. Min Act: -0.1700
Data Index: 2298153 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5236. Min Range: -6.5236
Max Act: 6.0236. Min Act: -0.1700
Data Index: 8821133 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5236. Min Range: -6.5236
Max Act: 6.0236. Min Act: -0.1700
Data Index: 34163 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5236. Min Range: -6.5236
Max Act: 5.9923. Min Act: -0.1700
Data Index: 7052583 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5236. Min Range: -6.5236
Max Act: 5.9923. Min Act: -0.1700
Data Index: 6915063 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5236. Min Range: -6.5236
Max Act: 5.9611. Min Act: -0.1700
Data Index: 2989392 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5236. Min Range: -6.5236
Max Act: 5.9298. Min Act: -0.1700
Data Index: 4108367 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5236. Min Range: -6.5236
Max Act: 5.9298. Min Act: -0.1700
Data Index: 4357676 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5236. Min Range: -6.5236
Max Act: 5.8986. Min Act: -0.1700
Data Index: 5437540 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5236. Min Range: -6.5236
Max Act: 5.8673. Min Act: -0.1700
Data Index: 2751770 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5236. Min Range: -6.5236
Max Act: 5.8361. Min Act: -0.1700
Data Index: 5290916 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5236. Min Range: -6.5236
Max Act: 5.8361. Min Act: -0.1700
Data Index: 5793325 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19