Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 237 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8917. Min Range: -2.8917
Max Act: 2.8917. Min Act: -0.1700
Data Index: 4042698 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8917. Min Range: -2.8917
Max Act: 2.8917. Min Act: -0.1700
Data Index: 4576665 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8917. Min Range: -2.8917
Max Act: 2.8441. Min Act: -0.1700
Data Index: 4145113 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8917. Min Range: -2.8917
Max Act: 2.8441. Min Act: -0.1700
Data Index: 5560216 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8917. Min Range: -2.8917
Max Act: 2.8123. Min Act: -0.1700
Data Index: 2957182 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8917. Min Range: -2.8917
Max Act: 2.8123. Min Act: -0.1700
Data Index: 5733829 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8917. Min Range: -2.8917
Max Act: 2.7804. Min Act: -0.1700
Data Index: 3246018 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8917. Min Range: -2.8917
Max Act: 2.7804. Min Act: -0.1700
Data Index: 3731208 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8917. Min Range: -2.8917
Max Act: 2.7964. Min Act: -0.1700
Data Index: 2158636 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8917. Min Range: -2.8917
Max Act: 2.7645. Min Act: -0.1700
Data Index: 5165743 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8917. Min Range: -2.8917
Max Act: 2.7645. Min Act: -0.1700
Data Index: 3947000 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8917. Min Range: -2.8917
Max Act: 2.7326. Min Act: -0.1700
Data Index: 808234 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8917. Min Range: -2.8917
Max Act: 2.7326. Min Act: -0.1700
Data Index: 5995807 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8917. Min Range: -2.8917
Max Act: 2.7006. Min Act: -0.1700
Data Index: 6749438 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8917. Min Range: -2.8917
Max Act: 2.7006. Min Act: -0.1700
Data Index: 3408696 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8917. Min Range: -2.8917
Max Act: 2.7006. Min Act: -0.1700
Data Index: 8064837 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8917. Min Range: -2.8917
Max Act: 2.7006. Min Act: -0.1700
Data Index: 8533493 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8917. Min Range: -2.8917
Max Act: 2.7006. Min Act: -0.1700
Data Index: 846242 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8917. Min Range: -2.8917
Max Act: 2.6846. Min Act: -0.1700
Data Index: 8770601 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8917. Min Range: -2.8917
Max Act: 2.7006. Min Act: -0.1700
Data Index: 1329308 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19