Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3369 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8563. Min Range: -8.8563
Max Act: 8.8563. Min Act: -0.1700
Data Index: 6170373 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8563. Min Range: -8.8563
Max Act: 8.7938. Min Act: -0.1700
Data Index: 8071331 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8563. Min Range: -8.8563
Max Act: 8.7313. Min Act: -0.1700
Data Index: 1129161 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8563. Min Range: -8.8563
Max Act: 8.7313. Min Act: -0.1700
Data Index: 1125076 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8563. Min Range: -8.8563
Max Act: 8.7313. Min Act: -0.1700
Data Index: 8335726 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8563. Min Range: -8.8563
Max Act: 8.6688. Min Act: -0.1700
Data Index: 3450236 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8563. Min Range: -8.8563
Max Act: 8.6688. Min Act: -0.1700
Data Index: 4429357 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8563. Min Range: -8.8563
Max Act: 8.6688. Min Act: -0.1700
Data Index: 2047420 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8563. Min Range: -8.8563
Max Act: 8.6063. Min Act: -0.1700
Data Index: 7946175 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8563. Min Range: -8.8563
Max Act: 8.5438. Min Act: -0.1700
Data Index: 3289942 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8563. Min Range: -8.8563
Max Act: 8.5438. Min Act: -0.1700
Data Index: 3843886 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8563. Min Range: -8.8563
Max Act: 8.5438. Min Act: -0.1700
Data Index: 1706391 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8563. Min Range: -8.8563
Max Act: 8.4813. Min Act: -0.1700
Data Index: 8272900 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8563. Min Range: -8.8563
Max Act: 8.4813. Min Act: -0.1700
Data Index: 1535738 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8563. Min Range: -8.8563
Max Act: 8.4813. Min Act: -0.1700
Data Index: 1223777 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8563. Min Range: -8.8563
Max Act: 8.4813. Min Act: -0.1700
Data Index: 2392141 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8563. Min Range: -8.8563
Max Act: 8.4813. Min Act: -0.1700
Data Index: 2710741 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8563. Min Range: -8.8563
Max Act: 8.4188. Min Act: -0.1700
Data Index: 6523146 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8563. Min Range: -8.8563
Max Act: 8.4188. Min Act: -0.1700
Data Index: 602965 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8563. Min Range: -8.8563
Max Act: 8.4188. Min Act: -0.1700
Data Index: 1642909 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #19