Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3254 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2582. Min Range: -6.2582
Max Act: 6.2582. Min Act: -0.1700
Data Index: 3294921 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2582. Min Range: -6.2582
Max Act: 6.2270. Min Act: -0.1700
Data Index: 4147233 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2582. Min Range: -6.2582
Max Act: 6.1957. Min Act: -0.1700
Data Index: 3504807 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2582. Min Range: -6.2582
Max Act: 6.1020. Min Act: -0.1700
Data Index: 7295141 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2582. Min Range: -6.2582
Max Act: 6.1020. Min Act: -0.1700
Data Index: 5073893 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2582. Min Range: -6.2582
Max Act: 6.1020. Min Act: -0.1700
Data Index: 1086734 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2582. Min Range: -6.2582
Max Act: 6.0707. Min Act: -0.1700
Data Index: 8768303 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2582. Min Range: -6.2582
Max Act: 6.0395. Min Act: -0.1700
Data Index: 8374010 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2582. Min Range: -6.2582
Max Act: 6.0082. Min Act: -0.1700
Data Index: 8130971 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2582. Min Range: -6.2582
Max Act: 6.0395. Min Act: -0.1700
Data Index: 6118511 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2582. Min Range: -6.2582
Max Act: 6.0395. Min Act: -0.1700
Data Index: 5678927 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2582. Min Range: -6.2582
Max Act: 6.0082. Min Act: -0.1700
Data Index: 1614466 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2582. Min Range: -6.2582
Max Act: 6.0082. Min Act: -0.1700
Data Index: 2001612 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2582. Min Range: -6.2582
Max Act: 6.0082. Min Act: -0.1700
Data Index: 8088695 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2582. Min Range: -6.2582
Max Act: 5.9770. Min Act: -0.1700
Data Index: 7907277 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2582. Min Range: -6.2582
Max Act: 5.9770. Min Act: -0.1700
Data Index: 4851732 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2582. Min Range: -6.2582
Max Act: 5.9770. Min Act: -0.1700
Data Index: 3220366 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2582. Min Range: -6.2582
Max Act: 5.9457. Min Act: -0.1700
Data Index: 4147133 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2582. Min Range: -6.2582
Max Act: 5.9457. Min Act: -0.1700
Data Index: 5121959 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2582. Min Range: -6.2582
Max Act: 5.9457. Min Act: -0.1700
Data Index: 7360985 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19