Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2018 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7390. Min Range: -5.7390
Max Act: 5.7390. Min Act: -0.1700
Data Index: 7553772 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7390. Min Range: -5.7390
Max Act: 5.7077. Min Act: -0.1700
Data Index: 7553773 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7390. Min Range: -5.7390
Max Act: 5.6765. Min Act: -0.1700
Data Index: 8792664 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7390. Min Range: -5.7390
Max Act: 5.6765. Min Act: -0.1700
Data Index: 5401605 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7390. Min Range: -5.7390
Max Act: 5.6140. Min Act: -0.1700
Data Index: 6621230 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7390. Min Range: -5.7390
Max Act: 5.6140. Min Act: -0.1700
Data Index: 1983 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7390. Min Range: -5.7390
Max Act: 5.5827. Min Act: -0.1700
Data Index: 6957983 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7390. Min Range: -5.7390
Max Act: 5.5515. Min Act: -0.1700
Data Index: 2213119 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7390. Min Range: -5.7390
Max Act: 5.5515. Min Act: -0.1700
Data Index: 2407416 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7390. Min Range: -5.7390
Max Act: 5.5202. Min Act: -0.1700
Data Index: 1315793 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7390. Min Range: -5.7390
Max Act: 5.5202. Min Act: -0.1700
Data Index: 3407364 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7390. Min Range: -5.7390
Max Act: 5.5202. Min Act: -0.1700
Data Index: 1308910 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7390. Min Range: -5.7390
Max Act: 5.4890. Min Act: -0.1700
Data Index: 5667053 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7390. Min Range: -5.7390
Max Act: 5.4577. Min Act: -0.1700
Data Index: 1458517 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7390. Min Range: -5.7390
Max Act: 5.4890. Min Act: -0.1700
Data Index: 2572372 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7390. Min Range: -5.7390
Max Act: 5.4577. Min Act: -0.1700
Data Index: 1544831 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7390. Min Range: -5.7390
Max Act: 5.4890. Min Act: -0.1700
Data Index: 5418942 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7390. Min Range: -5.7390
Max Act: 5.4890. Min Act: -0.1700
Data Index: 7877405 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7390. Min Range: -5.7390
Max Act: 5.4577. Min Act: -0.1700
Data Index: 2439038 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7390. Min Range: -5.7390
Max Act: 5.4577. Min Act: -0.1700
Data Index: 2532112 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19