Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2724 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5789. Min Range: -3.5789
Max Act: 3.5789. Min Act: -0.1700
Data Index: 7274333 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5789. Min Range: -3.5789
Max Act: 3.5632. Min Act: -0.1700
Data Index: 273841 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5789. Min Range: -3.5789
Max Act: 3.4849. Min Act: -0.1700
Data Index: 7000197 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5789. Min Range: -3.5789
Max Act: 3.4536. Min Act: -0.1700
Data Index: 4501172 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5789. Min Range: -3.5789
Max Act: 3.4693. Min Act: -0.1700
Data Index: 4127828 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5789. Min Range: -3.5789
Max Act: 3.4536. Min Act: -0.1700
Data Index: 4441981 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5789. Min Range: -3.5789
Max Act: 3.4536. Min Act: -0.1700
Data Index: 6950826 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5789. Min Range: -3.5789
Max Act: 3.4693. Min Act: -0.1700
Data Index: 2388338 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5789. Min Range: -3.5789
Max Act: 3.4379. Min Act: -0.1700
Data Index: 7172151 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5789. Min Range: -3.5789
Max Act: 3.4379. Min Act: -0.1700
Data Index: 5308298 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5789. Min Range: -3.5789
Max Act: 3.4536. Min Act: -0.1700
Data Index: 268728 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5789. Min Range: -3.5789
Max Act: 3.4223. Min Act: -0.1700
Data Index: 4001154 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5789. Min Range: -3.5789
Max Act: 3.4223. Min Act: -0.1700
Data Index: 8039046 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5789. Min Range: -3.5789
Max Act: 3.4379. Min Act: -0.1700
Data Index: 3876162 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5789. Min Range: -3.5789
Max Act: 3.4379. Min Act: -0.1700
Data Index: 3598163 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5789. Min Range: -3.5789
Max Act: 3.4379. Min Act: -0.1700
Data Index: 1793251 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5789. Min Range: -3.5789
Max Act: 3.4066. Min Act: -0.1700
Data Index: 683552 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5789. Min Range: -3.5789
Max Act: 3.4223. Min Act: -0.1700
Data Index: 207350 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5789. Min Range: -3.5789
Max Act: 3.4223. Min Act: -0.1700
Data Index: 6293231 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5789. Min Range: -3.5789
Max Act: 3.4223. Min Act: -0.1700
Data Index: 4743986 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19