Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4982 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2221. Min Range: -10.2221
Max Act: 10.2221. Min Act: -0.1700
Data Index: 1227223 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2221. Min Range: -10.2221
Max Act: 10.0971. Min Act: -0.1700
Data Index: 8672602 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2221. Min Range: -10.2221
Max Act: 9.9721. Min Act: -0.1700
Data Index: 7220828 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2221. Min Range: -10.2221
Max Act: 9.8471. Min Act: -0.1700
Data Index: 5011622 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2221. Min Range: -10.2221
Max Act: 9.8471. Min Act: -0.1700
Data Index: 6275053 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2221. Min Range: -10.2221
Max Act: 9.7221. Min Act: -0.1700
Data Index: 7803703 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2221. Min Range: -10.2221
Max Act: 9.6596. Min Act: -0.1700
Data Index: 5626391 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2221. Min Range: -10.2221
Max Act: 9.6596. Min Act: -0.1700
Data Index: 3305456 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2221. Min Range: -10.2221
Max Act: 9.5971. Min Act: -0.1700
Data Index: 2561982 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2221. Min Range: -10.2221
Max Act: 9.5346. Min Act: -0.1700
Data Index: 508642 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2221. Min Range: -10.2221
Max Act: 9.5971. Min Act: -0.1700
Data Index: 8572013 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2221. Min Range: -10.2221
Max Act: 9.5971. Min Act: -0.1700
Data Index: 3301983 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2221. Min Range: -10.2221
Max Act: 9.5346. Min Act: -0.1700
Data Index: 3495644 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2221. Min Range: -10.2221
Max Act: 9.5346. Min Act: -0.1700
Data Index: 7503516 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2221. Min Range: -10.2221
Max Act: 9.5346. Min Act: -0.1700
Data Index: 6883173 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2221. Min Range: -10.2221
Max Act: 9.4721. Min Act: -0.1700
Data Index: 4370407 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2221. Min Range: -10.2221
Max Act: 9.4721. Min Act: -0.1700
Data Index: 3131057 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2221. Min Range: -10.2221
Max Act: 9.4721. Min Act: -0.1700
Data Index: 2386937 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2221. Min Range: -10.2221
Max Act: 9.4096. Min Act: -0.1700
Data Index: 5245863 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2221. Min Range: -10.2221
Max Act: 9.4096. Min Act: -0.1700
Data Index: 50936 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19