Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 64 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0244. Min Range: -8.0244
Max Act: 8.0244. Min Act: -0.1700
Data Index: 4644208 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.9619. Min Act: -0.1700
Data Index: 8765135 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.7119. Min Act: -0.1700
Data Index: 2941026 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.5244. Min Act: -0.1700
Data Index: 561390 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.3994. Min Act: -0.1700
Data Index: 3512707 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.4306. Min Act: -0.1700
Data Index: 3013574 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.3369. Min Act: -0.1700
Data Index: 968889 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.3369. Min Act: -0.1700
Data Index: 2571842 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.2431. Min Act: -0.1700
Data Index: 1067013 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.2744. Min Act: -0.1700
Data Index: 5629457 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.2744. Min Act: -0.1700
Data Index: 1490260 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.2431. Min Act: -0.1700
Data Index: 7589187 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.2431. Min Act: -0.1700
Data Index: 8092127 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.1806. Min Act: -0.1700
Data Index: 1067809 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.1494. Min Act: -0.1700
Data Index: 8456345 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.1494. Min Act: -0.1700
Data Index: 7583147 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.1494. Min Act: -0.1700
Data Index: 4833932 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.1494. Min Act: -0.1700
Data Index: 1527699 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.1181. Min Act: -0.1700
Data Index: 954396 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0244. Min Range: -8.0244
Max Act: 7.1181. Min Act: -0.1700
Data Index: 3359504 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19