Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1690 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5137. Min Range: -4.5137
Max Act: 4.5137. Min Act: -0.1700
Data Index: 641850 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5137. Min Range: -4.5137
Max Act: 4.5137. Min Act: -0.1700
Data Index: 8742046 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5137. Min Range: -4.5137
Max Act: 4.4824. Min Act: -0.1700
Data Index: 2449266 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5137. Min Range: -4.5137
Max Act: 4.4512. Min Act: -0.1700
Data Index: 595391 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5137. Min Range: -4.5137
Max Act: 4.2637. Min Act: -0.1700
Data Index: 6377088 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5137. Min Range: -4.5137
Max Act: 4.2324. Min Act: -0.1700
Data Index: 3009184 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5137. Min Range: -4.5137
Max Act: 4.2011. Min Act: -0.1700
Data Index: 73825 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5137. Min Range: -4.5137
Max Act: 4.1699. Min Act: -0.1700
Data Index: 2951047 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5137. Min Range: -4.5137
Max Act: 4.2011. Min Act: -0.1700
Data Index: 987536 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5137. Min Range: -4.5137
Max Act: 4.1699. Min Act: -0.1700
Data Index: 5210206 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5137. Min Range: -4.5137
Max Act: 4.2011. Min Act: -0.1700
Data Index: 5075317 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5137. Min Range: -4.5137
Max Act: 4.2011. Min Act: -0.1700
Data Index: 7222082 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5137. Min Range: -4.5137
Max Act: 4.1699. Min Act: -0.1700
Data Index: 4731299 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5137. Min Range: -4.5137
Max Act: 4.1074. Min Act: -0.1700
Data Index: 7354458 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5137. Min Range: -4.5137
Max Act: 4.1386. Min Act: -0.1700
Data Index: 3593007 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5137. Min Range: -4.5137
Max Act: 4.1386. Min Act: -0.1700
Data Index: 7923056 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5137. Min Range: -4.5137
Max Act: 4.1074. Min Act: -0.1700
Data Index: 4429822 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5137. Min Range: -4.5137
Max Act: 4.0761. Min Act: -0.1700
Data Index: 8786552 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5137. Min Range: -4.5137
Max Act: 4.0449. Min Act: -0.1700
Data Index: 7722394 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5137. Min Range: -4.5137
Max Act: 4.0761. Min Act: -0.1700
Data Index: 315899 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19