Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2769 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.5441. Min Range: -8.5441
Max Act: 8.5441. Min Act: -0.1700
Data Index: 2154805 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5441. Min Range: -8.5441
Max Act: 8.4191. Min Act: -0.1700
Data Index: 1916077 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5441. Min Range: -8.5441
Max Act: 8.1066. Min Act: -0.1700
Data Index: 3990144 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5441. Min Range: -8.5441
Max Act: 7.9816. Min Act: -0.1700
Data Index: 3604885 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5441. Min Range: -8.5441
Max Act: 7.9816. Min Act: -0.1700
Data Index: 4075230 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5441. Min Range: -8.5441
Max Act: 7.8566. Min Act: -0.1700
Data Index: 4875902 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5441. Min Range: -8.5441
Max Act: 7.8566. Min Act: -0.1700
Data Index: 7829952 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5441. Min Range: -8.5441
Max Act: 7.7316. Min Act: -0.1700
Data Index: 1767301 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5441. Min Range: -8.5441
Max Act: 7.6691. Min Act: -0.1700
Data Index: 1039137 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5441. Min Range: -8.5441
Max Act: 7.7628. Min Act: -0.1700
Data Index: 327677 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5441. Min Range: -8.5441
Max Act: 7.5753. Min Act: -0.1700
Data Index: 8393863 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5441. Min Range: -8.5441
Max Act: 7.5441. Min Act: -0.1700
Data Index: 5311543 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5441. Min Range: -8.5441
Max Act: 7.5128. Min Act: -0.1700
Data Index: 5352479 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5441. Min Range: -8.5441
Max Act: 7.5441. Min Act: -0.1700
Data Index: 2792025 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5441. Min Range: -8.5441
Max Act: 7.5128. Min Act: -0.1700
Data Index: 250336 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5441. Min Range: -8.5441
Max Act: 7.5441. Min Act: -0.1700
Data Index: 3279230 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5441. Min Range: -8.5441
Max Act: 7.5128. Min Act: -0.1700
Data Index: 8108573 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5441. Min Range: -8.5441
Max Act: 7.5128. Min Act: -0.1700
Data Index: 2388110 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5441. Min Range: -8.5441
Max Act: 7.5441. Min Act: -0.1700
Data Index: 7243932 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5441. Min Range: -8.5441
Max Act: 7.5441. Min Act: -0.1700
Data Index: 3542229 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19