Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1412 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3104. Min Range: -5.3104
Max Act: 5.3104. Min Act: -0.1700
Data Index: 4254261 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3104. Min Range: -5.3104
Max Act: 5.1229. Min Act: -0.1700
Data Index: 7231065 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3104. Min Range: -5.3104
Max Act: 4.8729. Min Act: -0.1700
Data Index: 3488049 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3104. Min Range: -5.3104
Max Act: 4.8104. Min Act: -0.1700
Data Index: 4623783 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3104. Min Range: -5.3104
Max Act: 4.7791. Min Act: -0.1700
Data Index: 602628 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3104. Min Range: -5.3104
Max Act: 4.7479. Min Act: -0.1700
Data Index: 851602 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3104. Min Range: -5.3104
Max Act: 4.7479. Min Act: -0.1700
Data Index: 146558 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3104. Min Range: -5.3104
Max Act: 4.7479. Min Act: -0.1700
Data Index: 7316188 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3104. Min Range: -5.3104
Max Act: 4.6854. Min Act: -0.1700
Data Index: 5957477 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3104. Min Range: -5.3104
Max Act: 4.7166. Min Act: -0.1700
Data Index: 3129981 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3104. Min Range: -5.3104
Max Act: 4.7166. Min Act: -0.1700
Data Index: 7197789 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3104. Min Range: -5.3104
Max Act: 4.7166. Min Act: -0.1700
Data Index: 4839070 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3104. Min Range: -5.3104
Max Act: 4.6854. Min Act: -0.1700
Data Index: 4142279 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3104. Min Range: -5.3104
Max Act: 4.6854. Min Act: -0.1700
Data Index: 1228192 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3104. Min Range: -5.3104
Max Act: 4.6854. Min Act: -0.1700
Data Index: 2585193 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3104. Min Range: -5.3104
Max Act: 4.6541. Min Act: -0.1700
Data Index: 6725633 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3104. Min Range: -5.3104
Max Act: 4.6541. Min Act: -0.1700
Data Index: 501961 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3104. Min Range: -5.3104
Max Act: 4.6541. Min Act: -0.1700
Data Index: 3762630 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3104. Min Range: -5.3104
Max Act: 4.6541. Min Act: -0.1700
Data Index: 1764564 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3104. Min Range: -5.3104
Max Act: 4.6229. Min Act: -0.1700
Data Index: 6764461 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19