Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2679 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7954. Min Range: -2.7954
Max Act: 2.7954. Min Act: -0.1700
Data Index: 1519364 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7954. Min Range: -2.7954
Max Act: 2.6515. Min Act: -0.1700
Data Index: 8565860 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7954. Min Range: -2.7954
Max Act: 2.5872. Min Act: -0.1700
Data Index: 2280555 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7954. Min Range: -2.7954
Max Act: 2.6033. Min Act: -0.1700
Data Index: 3032760 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7954. Min Range: -2.7954
Max Act: 2.5550. Min Act: -0.1700
Data Index: 580797 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7954. Min Range: -2.7954
Max Act: 2.5227. Min Act: -0.1700
Data Index: 8063150 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7954. Min Range: -2.7954
Max Act: 2.5227. Min Act: -0.1700
Data Index: 5289482 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7954. Min Range: -2.7954
Max Act: 2.5065. Min Act: -0.1700
Data Index: 6143135 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7954. Min Range: -2.7954
Max Act: 2.4741. Min Act: -0.1700
Data Index: 8495209 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7954. Min Range: -2.7954
Max Act: 2.4741. Min Act: -0.1700
Data Index: 6852045 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7954. Min Range: -2.7954
Max Act: 2.4741. Min Act: -0.1700
Data Index: 3510130 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7954. Min Range: -2.7954
Max Act: 2.4416. Min Act: -0.1700
Data Index: 105529 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7954. Min Range: -2.7954
Max Act: 2.4416. Min Act: -0.1700
Data Index: 276017 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7954. Min Range: -2.7954
Max Act: 2.4416. Min Act: -0.1700
Data Index: 7129382 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7954. Min Range: -2.7954
Max Act: 2.4090. Min Act: -0.1700
Data Index: 2462190 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7954. Min Range: -2.7954
Max Act: 2.4253. Min Act: -0.1700
Data Index: 372814 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7954. Min Range: -2.7954
Max Act: 2.4253. Min Act: -0.1700
Data Index: 2076980 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7954. Min Range: -2.7954
Max Act: 2.4253. Min Act: -0.1700
Data Index: 7292066 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7954. Min Range: -2.7954
Max Act: 2.4090. Min Act: -0.1700
Data Index: 2541060 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7954. Min Range: -2.7954
Max Act: 2.4090. Min Act: -0.1700
Data Index: 3449506 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19