Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3577 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3349. Min Range: -7.3349
Max Act: 7.3349. Min Act: -0.1700
Data Index: 50737 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3349. Min Range: -7.3349
Max Act: 7.2724. Min Act: -0.1700
Data Index: 1797918 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3349. Min Range: -7.3349
Max Act: 7.1474. Min Act: -0.1700
Data Index: 1704001 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3349. Min Range: -7.3349
Max Act: 7.1161. Min Act: -0.1700
Data Index: 2854095 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3349. Min Range: -7.3349
Max Act: 7.1161. Min Act: -0.1700
Data Index: 6483864 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3349. Min Range: -7.3349
Max Act: 6.9911. Min Act: -0.1700
Data Index: 5833697 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3349. Min Range: -7.3349
Max Act: 6.9599. Min Act: -0.1700
Data Index: 6690190 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3349. Min Range: -7.3349
Max Act: 6.9599. Min Act: -0.1700
Data Index: 4693733 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3349. Min Range: -7.3349
Max Act: 6.9599. Min Act: -0.1700
Data Index: 6788491 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3349. Min Range: -7.3349
Max Act: 6.9286. Min Act: -0.1700
Data Index: 202996 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3349. Min Range: -7.3349
Max Act: 6.9599. Min Act: -0.1700
Data Index: 4869133 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3349. Min Range: -7.3349
Max Act: 6.8661. Min Act: -0.1700
Data Index: 6776455 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3349. Min Range: -7.3349
Max Act: 6.8661. Min Act: -0.1700
Data Index: 8597248 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3349. Min Range: -7.3349
Max Act: 6.8036. Min Act: -0.1700
Data Index: 404764 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3349. Min Range: -7.3349
Max Act: 6.8349. Min Act: -0.1700
Data Index: 6128202 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3349. Min Range: -7.3349
Max Act: 6.8036. Min Act: -0.1700
Data Index: 2668569 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3349. Min Range: -7.3349
Max Act: 6.8036. Min Act: -0.1700
Data Index: 6088952 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3349. Min Range: -7.3349
Max Act: 6.8036. Min Act: -0.1700
Data Index: 8304472 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3349. Min Range: -7.3349
Max Act: 6.8036. Min Act: -0.1700
Data Index: 3621061 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3349. Min Range: -7.3349
Max Act: 6.8036. Min Act: -0.1700
Data Index: 5827788 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19