Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1137 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8798. Min Range: -3.8798
Max Act: 3.8798. Min Act: -0.1700
Data Index: 7506910 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8798. Min Range: -3.8798
Max Act: 3.8485. Min Act: -0.1700
Data Index: 2721791 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8798. Min Range: -3.8798
Max Act: 3.8485. Min Act: -0.1700
Data Index: 8794162 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8798. Min Range: -3.8798
Max Act: 3.7860. Min Act: -0.1700
Data Index: 6167031 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8798. Min Range: -3.8798
Max Act: 3.7860. Min Act: -0.1700
Data Index: 4753279 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8798. Min Range: -3.8798
Max Act: 3.7234. Min Act: -0.1700
Data Index: 3758090 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8798. Min Range: -3.8798
Max Act: 3.7547. Min Act: -0.1700
Data Index: 1228453 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8798. Min Range: -3.8798
Max Act: 3.7234. Min Act: -0.1700
Data Index: 2238002 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8798. Min Range: -3.8798
Max Act: 3.6921. Min Act: -0.1700
Data Index: 2452279 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8798. Min Range: -3.8798
Max Act: 3.6921. Min Act: -0.1700
Data Index: 2720261 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8798. Min Range: -3.8798
Max Act: 3.6608. Min Act: -0.1700
Data Index: 3723583 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8798. Min Range: -3.8798
Max Act: 3.6295. Min Act: -0.1700
Data Index: 2628818 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8798. Min Range: -3.8798
Max Act: 3.6921. Min Act: -0.1700
Data Index: 49092 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8798. Min Range: -3.8798
Max Act: 3.6608. Min Act: -0.1700
Data Index: 5755559 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8798. Min Range: -3.8798
Max Act: 3.6295. Min Act: -0.1700
Data Index: 5420647 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8798. Min Range: -3.8798
Max Act: 3.6295. Min Act: -0.1700
Data Index: 4770377 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8798. Min Range: -3.8798
Max Act: 3.5982. Min Act: -0.1700
Data Index: 8314261 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8798. Min Range: -3.8798
Max Act: 3.6295. Min Act: -0.1700
Data Index: 6392625 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8798. Min Range: -3.8798
Max Act: 3.6295. Min Act: -0.1700
Data Index: 2041337 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8798. Min Range: -3.8798
Max Act: 3.5982. Min Act: -0.1700
Data Index: 3373082 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19