Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1621 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.2265. Min Range: -1.2265
Max Act: 1.2265. Min Act: -0.1700
Data Index: 5856256 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2265. Min Range: -1.2265
Max Act: 1.2088. Min Act: -0.1700
Data Index: 5794 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2265. Min Range: -1.2265
Max Act: 1.1824. Min Act: -0.1700
Data Index: 7633440 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2265. Min Range: -1.2265
Max Act: 1.1736. Min Act: -0.1700
Data Index: 7633438 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2265. Min Range: -1.2265
Max Act: 1.1648. Min Act: -0.1700
Data Index: 7983524 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2265. Min Range: -1.2265
Max Act: 1.1648. Min Act: -0.1700
Data Index: 7487422 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2265. Min Range: -1.2265
Max Act: 1.1561. Min Act: -0.1700
Data Index: 5979490 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2265. Min Range: -1.2265
Max Act: 1.1561. Min Act: -0.1700
Data Index: 2137684 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2265. Min Range: -1.2265
Max Act: 1.1473. Min Act: -0.1700
Data Index: 7166503 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2265. Min Range: -1.2265
Max Act: 1.1473. Min Act: -0.1700
Data Index: 4229990 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2265. Min Range: -1.2265
Max Act: 1.1473. Min Act: -0.1700
Data Index: 3959412 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2265. Min Range: -1.2265
Max Act: 1.1385. Min Act: -0.1700
Data Index: 3353479 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2265. Min Range: -1.2265
Max Act: 1.1473. Min Act: -0.1700
Data Index: 2703216 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2265. Min Range: -1.2265
Max Act: 1.1473. Min Act: -0.1700
Data Index: 7166498 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2265. Min Range: -1.2265
Max Act: 1.1297. Min Act: -0.1700
Data Index: 734014 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2265. Min Range: -1.2265
Max Act: 1.1385. Min Act: -0.1700
Data Index: 1437201 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2265. Min Range: -1.2265
Max Act: 1.1385. Min Act: -0.1700
Data Index: 7875806 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2265. Min Range: -1.2265
Max Act: 1.1385. Min Act: -0.1700
Data Index: 7875805 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2265. Min Range: -1.2265
Max Act: 1.1385. Min Act: -0.1700
Data Index: 7875812 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2265. Min Range: -1.2265
Max Act: 1.1473. Min Act: -0.1700
Data Index: 4570164 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19