Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5197 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4201. Min Range: -3.4201
Max Act: 3.4201. Min Act: -0.1700
Data Index: 5493511 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4201. Min Range: -3.4201
Max Act: 3.4044. Min Act: -0.1700
Data Index: 7904118 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4201. Min Range: -3.4201
Max Act: 3.3731. Min Act: -0.1700
Data Index: 6607997 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4201. Min Range: -3.4201
Max Act: 3.3574. Min Act: -0.1700
Data Index: 3109550 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4201. Min Range: -3.4201
Max Act: 3.3574. Min Act: -0.1700
Data Index: 1198624 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4201. Min Range: -3.4201
Max Act: 3.3417. Min Act: -0.1700
Data Index: 7699535 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4201. Min Range: -3.4201
Max Act: 3.3417. Min Act: -0.1700
Data Index: 1028442 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4201. Min Range: -3.4201
Max Act: 3.3417. Min Act: -0.1700
Data Index: 7592014 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4201. Min Range: -3.4201
Max Act: 3.2946. Min Act: -0.1700
Data Index: 3068236 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4201. Min Range: -3.4201
Max Act: 3.2946. Min Act: -0.1700
Data Index: 553453 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4201. Min Range: -3.4201
Max Act: 3.2789. Min Act: -0.1700
Data Index: 3805296 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4201. Min Range: -3.4201
Max Act: 3.2946. Min Act: -0.1700
Data Index: 3664477 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4201. Min Range: -3.4201
Max Act: 3.2789. Min Act: -0.1700
Data Index: 3190973 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4201. Min Range: -3.4201
Max Act: 3.2632. Min Act: -0.1700
Data Index: 4549922 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4201. Min Range: -3.4201
Max Act: 3.2475. Min Act: -0.1700
Data Index: 7407540 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4201. Min Range: -3.4201
Max Act: 3.2475. Min Act: -0.1700
Data Index: 2988091 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4201. Min Range: -3.4201
Max Act: 3.2475. Min Act: -0.1700
Data Index: 7699536 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4201. Min Range: -3.4201
Max Act: 3.2318. Min Act: -0.1700
Data Index: 7798666 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4201. Min Range: -3.4201
Max Act: 3.2161. Min Act: -0.1700
Data Index: 4994181 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4201. Min Range: -3.4201
Max Act: 3.2161. Min Act: -0.1700
Data Index: 7033492 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19