Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3236 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9468. Min Range: -6.9468
Max Act: 6.9468. Min Act: -0.1700
Data Index: 5424018 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9468. Min Range: -6.9468
Max Act: 6.9156. Min Act: -0.1700
Data Index: 3997684 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9468. Min Range: -6.9468
Max Act: 6.8843. Min Act: -0.1700
Data Index: 3390316 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9468. Min Range: -6.9468
Max Act: 6.8531. Min Act: -0.1700
Data Index: 5153635 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9468. Min Range: -6.9468
Max Act: 6.8218. Min Act: -0.1700
Data Index: 7653101 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9468. Min Range: -6.9468
Max Act: 6.7593. Min Act: -0.1700
Data Index: 4066146 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9468. Min Range: -6.9468
Max Act: 6.7281. Min Act: -0.1700
Data Index: 5538704 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9468. Min Range: -6.9468
Max Act: 6.6968. Min Act: -0.1700
Data Index: 8732697 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9468. Min Range: -6.9468
Max Act: 6.6656. Min Act: -0.1700
Data Index: 293927 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9468. Min Range: -6.9468
Max Act: 6.6031. Min Act: -0.1700
Data Index: 190123 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9468. Min Range: -6.9468
Max Act: 6.6031. Min Act: -0.1700
Data Index: 690866 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9468. Min Range: -6.9468
Max Act: 6.5406. Min Act: -0.1700
Data Index: 7367042 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9468. Min Range: -6.9468
Max Act: 6.5406. Min Act: -0.1700
Data Index: 7592140 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9468. Min Range: -6.9468
Max Act: 6.5406. Min Act: -0.1700
Data Index: 1983806 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9468. Min Range: -6.9468
Max Act: 6.4781. Min Act: -0.1700
Data Index: 2092651 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9468. Min Range: -6.9468
Max Act: 6.5093. Min Act: -0.1700
Data Index: 7985689 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9468. Min Range: -6.9468
Max Act: 6.4781. Min Act: -0.1700
Data Index: 6481988 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9468. Min Range: -6.9468
Max Act: 6.4781. Min Act: -0.1700
Data Index: 765117 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9468. Min Range: -6.9468
Max Act: 6.4781. Min Act: -0.1700
Data Index: 1745373 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9468. Min Range: -6.9468
Max Act: 6.5093. Min Act: -0.1700
Data Index: 4624768 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #19