Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1776 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4540. Min Range: -4.4540
Max Act: 4.4540. Min Act: -0.1700
Data Index: 3969648 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4540. Min Range: -4.4540
Max Act: 4.4540. Min Act: -0.1700
Data Index: 1952133 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4540. Min Range: -4.4540
Max Act: 4.4227. Min Act: -0.1700
Data Index: 3171332 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4540. Min Range: -4.4540
Max Act: 4.3915. Min Act: -0.1700
Data Index: 6953894 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4540. Min Range: -4.4540
Max Act: 4.3290. Min Act: -0.1697
Data Index: 2267872 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4540. Min Range: -4.4540
Max Act: 4.3602. Min Act: -0.1699
Data Index: 5559894 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4540. Min Range: -4.4540
Max Act: 4.3290. Min Act: -0.1700
Data Index: 7631367 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4540. Min Range: -4.4540
Max Act: 4.3290. Min Act: -0.1700
Data Index: 4865475 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4540. Min Range: -4.4540
Max Act: 4.3290. Min Act: -0.1700
Data Index: 6308878 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4540. Min Range: -4.4540
Max Act: 4.3290. Min Act: -0.1700
Data Index: 1173632 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4540. Min Range: -4.4540
Max Act: 4.2977. Min Act: -0.1700
Data Index: 4336733 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4540. Min Range: -4.4540
Max Act: 4.2977. Min Act: -0.1700
Data Index: 4399553 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4540. Min Range: -4.4540
Max Act: 4.2977. Min Act: -0.1700
Data Index: 3782305 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4540. Min Range: -4.4540
Max Act: 4.2665. Min Act: -0.1700
Data Index: 1363732 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4540. Min Range: -4.4540
Max Act: 4.2665. Min Act: -0.1700
Data Index: 2216598 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4540. Min Range: -4.4540
Max Act: 4.2665. Min Act: -0.1700
Data Index: 7516819 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4540. Min Range: -4.4540
Max Act: 4.2977. Min Act: -0.1700
Data Index: 4590511 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4540. Min Range: -4.4540
Max Act: 4.2665. Min Act: -0.1700
Data Index: 6294123 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4540. Min Range: -4.4540
Max Act: 4.2665. Min Act: -0.1700
Data Index: 1950002 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4540. Min Range: -4.4540
Max Act: 4.2665. Min Act: -0.1700
Data Index: 430615 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19