Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4635 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6270. Min Range: -5.6270
Max Act: 5.6270. Min Act: -0.1700
Data Index: 3855068 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6270. Min Range: -5.6270
Max Act: 5.5645. Min Act: -0.1700
Data Index: 1990328 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6270. Min Range: -5.6270
Max Act: 5.5332. Min Act: -0.1700
Data Index: 3605576 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6270. Min Range: -5.6270
Max Act: 5.5020. Min Act: -0.1700
Data Index: 8154266 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6270. Min Range: -5.6270
Max Act: 5.4707. Min Act: -0.1700
Data Index: 3845795 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6270. Min Range: -5.6270
Max Act: 5.4395. Min Act: -0.1700
Data Index: 5878748 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6270. Min Range: -5.6270
Max Act: 5.4395. Min Act: -0.1700
Data Index: 2985173 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6270. Min Range: -5.6270
Max Act: 5.4082. Min Act: -0.1700
Data Index: 4137806 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6270. Min Range: -5.6270
Max Act: 5.4082. Min Act: -0.1700
Data Index: 4954188 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6270. Min Range: -5.6270
Max Act: 5.4082. Min Act: -0.1700
Data Index: 660768 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6270. Min Range: -5.6270
Max Act: 5.4082. Min Act: -0.1700
Data Index: 187038 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6270. Min Range: -5.6270
Max Act: 5.4082. Min Act: -0.1700
Data Index: 6136463 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6270. Min Range: -5.6270
Max Act: 5.4082. Min Act: -0.1700
Data Index: 6748706 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6270. Min Range: -5.6270
Max Act: 5.3770. Min Act: -0.1700
Data Index: 6156417 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6270. Min Range: -5.6270
Max Act: 5.3770. Min Act: -0.1700
Data Index: 6303200 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6270. Min Range: -5.6270
Max Act: 5.3770. Min Act: -0.1700
Data Index: 1795751 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6270. Min Range: -5.6270
Max Act: 5.3770. Min Act: -0.1700
Data Index: 2171460 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6270. Min Range: -5.6270
Max Act: 5.3770. Min Act: -0.1700
Data Index: 3860862 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6270. Min Range: -5.6270
Max Act: 5.3457. Min Act: -0.1700
Data Index: 2675671 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6270. Min Range: -5.6270
Max Act: 5.3457. Min Act: -0.1700
Data Index: 2004239 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19