Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4902 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7332. Min Range: -4.7332
Max Act: 4.7332. Min Act: -0.1700
Data Index: 5613068 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7332. Min Range: -4.7332
Max Act: 4.6395. Min Act: -0.1700
Data Index: 1918590 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7332. Min Range: -4.7332
Max Act: 4.6395. Min Act: -0.1700
Data Index: 3475841 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7332. Min Range: -4.7332
Max Act: 4.6395. Min Act: -0.1700
Data Index: 1766686 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7332. Min Range: -4.7332
Max Act: 4.6395. Min Act: -0.1700
Data Index: 6706843 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7332. Min Range: -4.7332
Max Act: 4.6082. Min Act: -0.1700
Data Index: 2790210 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7332. Min Range: -4.7332
Max Act: 4.6082. Min Act: -0.1700
Data Index: 5338051 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7332. Min Range: -4.7332
Max Act: 4.6082. Min Act: -0.1700
Data Index: 4788083 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7332. Min Range: -4.7332
Max Act: 4.6082. Min Act: -0.1700
Data Index: 2790213 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7332. Min Range: -4.7332
Max Act: 4.5457. Min Act: -0.1700
Data Index: 4389234 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7332. Min Range: -4.7332
Max Act: 4.6082. Min Act: -0.1700
Data Index: 6105167 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7332. Min Range: -4.7332
Max Act: 4.5457. Min Act: -0.1700
Data Index: 5976796 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7332. Min Range: -4.7332
Max Act: 4.5144. Min Act: -0.1700
Data Index: 4140908 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7332. Min Range: -4.7332
Max Act: 4.5144. Min Act: -0.1700
Data Index: 6929431 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7332. Min Range: -4.7332
Max Act: 4.4832. Min Act: -0.1700
Data Index: 6783187 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7332. Min Range: -4.7332
Max Act: 4.4832. Min Act: -0.1700
Data Index: 7424763 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7332. Min Range: -4.7332
Max Act: 4.4832. Min Act: -0.1700
Data Index: 6357877 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7332. Min Range: -4.7332
Max Act: 4.4519. Min Act: -0.1700
Data Index: 3464374 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7332. Min Range: -4.7332
Max Act: 4.4519. Min Act: -0.1700
Data Index: 1983819 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7332. Min Range: -4.7332
Max Act: 4.4519. Min Act: -0.1700
Data Index: 6156684 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19