Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1747 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9287. Min Range: -5.9287
Max Act: 5.9287. Min Act: -0.1700
Data Index: 3005549 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9287. Min Range: -5.9287
Max Act: 5.8974. Min Act: -0.1700
Data Index: 6808216 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9287. Min Range: -5.9287
Max Act: 5.4599. Min Act: -0.1700
Data Index: 614161 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9287. Min Range: -5.9287
Max Act: 5.3349. Min Act: -0.1700
Data Index: 2871686 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9287. Min Range: -5.9287
Max Act: 5.2412. Min Act: -0.1700
Data Index: 2026108 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9287. Min Range: -5.9287
Max Act: 5.2412. Min Act: -0.1700
Data Index: 3184147 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9287. Min Range: -5.9287
Max Act: 5.2099. Min Act: -0.1700
Data Index: 7925374 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9287. Min Range: -5.9287
Max Act: 5.2099. Min Act: -0.1700
Data Index: 5495405 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9287. Min Range: -5.9287
Max Act: 5.2412. Min Act: -0.1700
Data Index: 395743 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9287. Min Range: -5.9287
Max Act: 5.2099. Min Act: -0.1700
Data Index: 787550 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9287. Min Range: -5.9287
Max Act: 5.2099. Min Act: -0.1700
Data Index: 7105295 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9287. Min Range: -5.9287
Max Act: 5.1787. Min Act: -0.1700
Data Index: 1483091 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9287. Min Range: -5.9287
Max Act: 5.1787. Min Act: -0.1700
Data Index: 2985881 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9287. Min Range: -5.9287
Max Act: 5.1474. Min Act: -0.1700
Data Index: 5461442 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9287. Min Range: -5.9287
Max Act: 5.1787. Min Act: -0.1700
Data Index: 568774 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9287. Min Range: -5.9287
Max Act: 5.1162. Min Act: -0.1700
Data Index: 32173 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9287. Min Range: -5.9287
Max Act: 5.1474. Min Act: -0.1700
Data Index: 797120 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9287. Min Range: -5.9287
Max Act: 5.1474. Min Act: -0.1700
Data Index: 6477560 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9287. Min Range: -5.9287
Max Act: 5.1787. Min Act: -0.1700
Data Index: 2200248 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9287. Min Range: -5.9287
Max Act: 5.1474. Min Act: -0.1700
Data Index: 1184659 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19