Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 126 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8287. Min Range: -1.8287
Max Act: 1.8287. Min Act: -0.1700
Data Index: 5824160 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8287. Min Range: -1.8287
Max Act: 1.8115. Min Act: -0.1664
Data Index: 1186195 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8287. Min Range: -1.8287
Max Act: 1.7857. Min Act: -0.1689
Data Index: 4699012 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8287. Min Range: -1.8287
Max Act: 1.7771. Min Act: -0.1700
Data Index: 663994 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8287. Min Range: -1.8287
Max Act: 1.7684. Min Act: -0.1700
Data Index: 5798799 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8287. Min Range: -1.8287
Max Act: 1.7684. Min Act: -0.1690
Data Index: 3831193 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8287. Min Range: -1.8287
Max Act: 1.7684. Min Act: -0.1700
Data Index: 2743603 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8287. Min Range: -1.8287
Max Act: 1.7771. Min Act: -0.1700
Data Index: 1701792 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8287. Min Range: -1.8287
Max Act: 1.7425. Min Act: -0.1700
Data Index: 4772317 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8287. Min Range: -1.8287
Max Act: 1.7425. Min Act: -0.1700
Data Index: 6665074 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8287. Min Range: -1.8287
Max Act: 1.7252. Min Act: -0.1700
Data Index: 6309887 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8287. Min Range: -1.8287
Max Act: 1.7339. Min Act: -0.1700
Data Index: 8559570 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8287. Min Range: -1.8287
Max Act: 1.7339. Min Act: -0.1700
Data Index: 4476761 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8287. Min Range: -1.8287
Max Act: 1.7425. Min Act: -0.1700
Data Index: 8733340 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8287. Min Range: -1.8287
Max Act: 1.7425. Min Act: -0.1700
Data Index: 7750609 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8287. Min Range: -1.8287
Max Act: 1.7166. Min Act: -0.1700
Data Index: 6119848 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8287. Min Range: -1.8287
Max Act: 1.6906. Min Act: -0.1700
Data Index: 3488278 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8287. Min Range: -1.8287
Max Act: 1.7166. Min Act: -0.1700
Data Index: 8303150 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8287. Min Range: -1.8287
Max Act: 1.7252. Min Act: -0.1693
Data Index: 1186204 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8287. Min Range: -1.8287
Max Act: 1.7166. Min Act: -0.1700
Data Index: 3563016 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19