Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 476 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6449. Min Range: -6.6449
Max Act: 6.6449. Min Act: -0.1700
Data Index: 6861710 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6449. Min Range: -6.6449
Max Act: 6.4887. Min Act: -0.1700
Data Index: 52459 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6449. Min Range: -6.6449
Max Act: 6.3949. Min Act: -0.1700
Data Index: 4461852 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6449. Min Range: -6.6449
Max Act: 6.3324. Min Act: -0.1700
Data Index: 1816037 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6449. Min Range: -6.6449
Max Act: 6.3324. Min Act: -0.1700
Data Index: 4225544 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6449. Min Range: -6.6449
Max Act: 6.3324. Min Act: -0.1700
Data Index: 2419834 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6449. Min Range: -6.6449
Max Act: 6.3324. Min Act: -0.1700
Data Index: 2320329 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6449. Min Range: -6.6449
Max Act: 6.3012. Min Act: -0.1700
Data Index: 7647477 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6449. Min Range: -6.6449
Max Act: 6.2699. Min Act: -0.1700
Data Index: 5402124 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6449. Min Range: -6.6449
Max Act: 6.2699. Min Act: -0.1700
Data Index: 6765135 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6449. Min Range: -6.6449
Max Act: 6.2699. Min Act: -0.1700
Data Index: 668619 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6449. Min Range: -6.6449
Max Act: 6.2387. Min Act: -0.1700
Data Index: 8525529 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6449. Min Range: -6.6449
Max Act: 6.2699. Min Act: -0.1700
Data Index: 4629023 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6449. Min Range: -6.6449
Max Act: 6.2074. Min Act: -0.1700
Data Index: 5259912 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6449. Min Range: -6.6449
Max Act: 6.2074. Min Act: -0.1700
Data Index: 667773 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6449. Min Range: -6.6449
Max Act: 6.2074. Min Act: -0.1700
Data Index: 6355032 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6449. Min Range: -6.6449
Max Act: 6.2074. Min Act: -0.1700
Data Index: 1564309 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6449. Min Range: -6.6449
Max Act: 6.1762. Min Act: -0.1700
Data Index: 6617160 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6449. Min Range: -6.6449
Max Act: 6.2074. Min Act: -0.1700
Data Index: 4474163 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6449. Min Range: -6.6449
Max Act: 6.1137. Min Act: -0.1700
Data Index: 288444 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #19