Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3992 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.8910. Min Act: -0.1700
Data Index: 4902070 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.8598. Min Act: -0.1700
Data Index: 3484001 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.8285. Min Act: -0.1700
Data Index: 2092786 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.7659. Min Act: -0.1700
Data Index: 4433180 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.7347. Min Act: -0.1700
Data Index: 3416483 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.7034. Min Act: -0.1700
Data Index: 819272 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.6721. Min Act: -0.1700
Data Index: 2139893 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.6721. Min Act: -0.1700
Data Index: 1951188 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.7034. Min Act: -0.1700
Data Index: 5313299 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.6721. Min Act: -0.1700
Data Index: 4887489 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.6408. Min Act: -0.1700
Data Index: 2307458 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.6095. Min Act: -0.1700
Data Index: 7547527 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.6252. Min Act: -0.1700
Data Index: 1396089 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.6095. Min Act: -0.1700
Data Index: 1619468 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.5939. Min Act: -0.1700
Data Index: 2171331 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.6095. Min Act: -0.1700
Data Index: 3622868 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.5939. Min Act: -0.1700
Data Index: 1653033 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.5939. Min Act: -0.1700
Data Index: 8166806 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.5625. Min Act: -0.1700
Data Index: 3752239 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8910. Min Range: -3.8910
Max Act: 3.5782. Min Act: -0.1700
Data Index: 5258560 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19