Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1919 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3525. Min Range: -5.3525
Max Act: 5.3525. Min Act: -0.1700
Data Index: 8041653 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3525. Min Range: -5.3525
Max Act: 5.3525. Min Act: -0.1700
Data Index: 3301646 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3525. Min Range: -5.3525
Max Act: 5.2900. Min Act: -0.1700
Data Index: 8489282 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3525. Min Range: -5.3525
Max Act: 5.2587. Min Act: -0.1700
Data Index: 1065006 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3525. Min Range: -5.3525
Max Act: 5.1962. Min Act: -0.1700
Data Index: 223093 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3525. Min Range: -5.3525
Max Act: 5.2275. Min Act: -0.1700
Data Index: 7025034 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3525. Min Range: -5.3525
Max Act: 5.1962. Min Act: -0.1700
Data Index: 6877977 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3525. Min Range: -5.3525
Max Act: 5.2275. Min Act: -0.1700
Data Index: 7892842 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3525. Min Range: -5.3525
Max Act: 5.1337. Min Act: -0.1700
Data Index: 1540186 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3525. Min Range: -5.3525
Max Act: 5.1650. Min Act: -0.1700
Data Index: 524574 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3525. Min Range: -5.3525
Max Act: 5.1025. Min Act: -0.1700
Data Index: 7636999 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3525. Min Range: -5.3525
Max Act: 5.1337. Min Act: -0.1700
Data Index: 3688358 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3525. Min Range: -5.3525
Max Act: 5.1337. Min Act: -0.1700
Data Index: 5421745 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3525. Min Range: -5.3525
Max Act: 5.1025. Min Act: -0.1700
Data Index: 2413675 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3525. Min Range: -5.3525
Max Act: 5.1025. Min Act: -0.1700
Data Index: 5758485 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3525. Min Range: -5.3525
Max Act: 5.0400. Min Act: -0.1700
Data Index: 3277060 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3525. Min Range: -5.3525
Max Act: 5.0087. Min Act: -0.1700
Data Index: 1710695 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3525. Min Range: -5.3525
Max Act: 5.0087. Min Act: -0.1700
Data Index: 7735731 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3525. Min Range: -5.3525
Max Act: 5.0087. Min Act: -0.1700
Data Index: 52921 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3525. Min Range: -5.3525
Max Act: 5.0400. Min Act: -0.1700
Data Index: 4301455 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19