Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1821 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.6339. Min Act: -0.1700
Data Index: 1227597 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.6339. Min Act: -0.1700
Data Index: 6066107 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.5089. Min Act: -0.1700
Data Index: 2352359 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.4151. Min Act: -0.1700
Data Index: 4107130 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.4151. Min Act: -0.1700
Data Index: 2713797 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.3526. Min Act: -0.1700
Data Index: 6697848 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.3214. Min Act: -0.1700
Data Index: 7692663 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.2589. Min Act: -0.1700
Data Index: 7316477 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.2589. Min Act: -0.1700
Data Index: 1214628 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.2589. Min Act: -0.1700
Data Index: 454107 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.2589. Min Act: -0.1700
Data Index: 2265587 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.2276. Min Act: -0.1700
Data Index: 4501643 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.1651. Min Act: -0.1700
Data Index: 7319839 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.1339. Min Act: -0.1700
Data Index: 2893770 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.0714. Min Act: -0.1700
Data Index: 2720435 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.1026. Min Act: -0.1700
Data Index: 5811846 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.1651. Min Act: -0.1700
Data Index: 2256373 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.1339. Min Act: -0.1700
Data Index: 4199996 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.1026. Min Act: -0.1700
Data Index: 5058848 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6339. Min Range: -7.6339
Max Act: 7.1026. Min Act: -0.1700
Data Index: 8510874 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19