Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4092 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0155. Min Range: -6.0155
Max Act: 6.0155. Min Act: -0.1700
Data Index: 6198797 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.8592. Min Act: -0.1700
Data Index: 6985230 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.7967. Min Act: -0.1700
Data Index: 3134419 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.8280. Min Act: -0.1700
Data Index: 3222355 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.7967. Min Act: -0.1700
Data Index: 3543936 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.7342. Min Act: -0.1700
Data Index: 3023816 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.7030. Min Act: -0.1700
Data Index: 6096290 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.7030. Min Act: -0.1700
Data Index: 3073063 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.7655. Min Act: -0.1700
Data Index: 2654202 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.7342. Min Act: -0.1700
Data Index: 6096287 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.7030. Min Act: -0.1700
Data Index: 1433852 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.6092. Min Act: -0.1700
Data Index: 1667948 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.5155. Min Act: -0.1700
Data Index: 1595373 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.5780. Min Act: -0.1700
Data Index: 4856272 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.5780. Min Act: -0.1700
Data Index: 5903628 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.5780. Min Act: -0.1700
Data Index: 484098 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.5780. Min Act: -0.1700
Data Index: 8676815 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.6092. Min Act: -0.1700
Data Index: 7071086 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.6092. Min Act: -0.1700
Data Index: 5606934 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.5467. Min Act: -0.1700
Data Index: 4038018 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19