Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3218 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.8298. Min Act: -0.1700
Data Index: 7771298 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.7359. Min Act: -0.1700
Data Index: 2020237 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.6890. Min Act: -0.1700
Data Index: 2577597 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.6108. Min Act: -0.1700
Data Index: 5625344 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.5951. Min Act: -0.1700
Data Index: 1064096 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.5482. Min Act: -0.1700
Data Index: 3254302 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.5795. Min Act: -0.1700
Data Index: 941437 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.5638. Min Act: -0.1700
Data Index: 2757631 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.5638. Min Act: -0.1700
Data Index: 8316221 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.5482. Min Act: -0.1700
Data Index: 7112758 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.5168. Min Act: -0.1700
Data Index: 6775135 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.5168. Min Act: -0.1700
Data Index: 8542769 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.5168. Min Act: -0.1700
Data Index: 2115368 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.5325. Min Act: -0.1700
Data Index: 8117219 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.5325. Min Act: -0.1700
Data Index: 6048228 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.5168. Min Act: -0.1700
Data Index: 77590 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.5012. Min Act: -0.1700
Data Index: 2007450 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.5012. Min Act: -0.1700
Data Index: 5555558 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.5012. Min Act: -0.1700
Data Index: 5657032 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8298. Min Range: -3.8298
Max Act: 3.4855. Min Act: -0.1700
Data Index: 3576439 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19