Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6196 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0334. Min Range: -8.0334
Max Act: 8.0334. Min Act: -0.1700
Data Index: 3845243 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0334. Min Range: -8.0334
Max Act: 8.0022. Min Act: -0.1700
Data Index: 8535199 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0334. Min Range: -8.0334
Max Act: 7.8772. Min Act: -0.1700
Data Index: 3733490 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0334. Min Range: -8.0334
Max Act: 7.8772. Min Act: -0.1700
Data Index: 1072623 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0334. Min Range: -8.0334
Max Act: 7.8459. Min Act: -0.1700
Data Index: 64284 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0334. Min Range: -8.0334
Max Act: 7.6897. Min Act: -0.1700
Data Index: 1555440 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0334. Min Range: -8.0334
Max Act: 7.6584. Min Act: -0.1700
Data Index: 4224229 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0334. Min Range: -8.0334
Max Act: 7.5959. Min Act: -0.1700
Data Index: 7301269 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0334. Min Range: -8.0334
Max Act: 7.5334. Min Act: -0.1700
Data Index: 8378352 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0334. Min Range: -8.0334
Max Act: 7.4084. Min Act: -0.1700
Data Index: 3384150 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0334. Min Range: -8.0334
Max Act: 7.4397. Min Act: -0.1700
Data Index: 6158714 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0334. Min Range: -8.0334
Max Act: 7.4397. Min Act: -0.1700
Data Index: 4971592 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0334. Min Range: -8.0334
Max Act: 7.4397. Min Act: -0.1700
Data Index: 7133547 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0334. Min Range: -8.0334
Max Act: 7.4397. Min Act: -0.1700
Data Index: 8522526 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0334. Min Range: -8.0334
Max Act: 7.4084. Min Act: -0.1700
Data Index: 5775735 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0334. Min Range: -8.0334
Max Act: 7.3772. Min Act: -0.1700
Data Index: 7378440 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0334. Min Range: -8.0334
Max Act: 7.3772. Min Act: -0.1700
Data Index: 8565630 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0334. Min Range: -8.0334
Max Act: 7.4084. Min Act: -0.1700
Data Index: 8434641 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0334. Min Range: -8.0334
Max Act: 7.3459. Min Act: -0.1700
Data Index: 2524896 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0334. Min Range: -8.0334
Max Act: 7.3772. Min Act: -0.1700
Data Index: 6699855 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19