Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 393 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5874. Min Range: -6.5874
Max Act: 6.5874. Min Act: -0.1700
Data Index: 6799171 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5874. Min Range: -6.5874
Max Act: 6.1499. Min Act: -0.1700
Data Index: 3698301 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5874. Min Range: -6.5874
Max Act: 6.1187. Min Act: -0.1700
Data Index: 3067172 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5874. Min Range: -6.5874
Max Act: 6.0562. Min Act: -0.1700
Data Index: 2380850 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5874. Min Range: -6.5874
Max Act: 5.8374. Min Act: -0.1700
Data Index: 4082985 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5874. Min Range: -6.5874
Max Act: 5.8062. Min Act: -0.1700
Data Index: 6541412 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5874. Min Range: -6.5874
Max Act: 5.8374. Min Act: -0.1700
Data Index: 5215894 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5874. Min Range: -6.5874
Max Act: 5.8374. Min Act: -0.1700
Data Index: 5933038 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5874. Min Range: -6.5874
Max Act: 5.8062. Min Act: -0.1700
Data Index: 5671534 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5874. Min Range: -6.5874
Max Act: 5.8062. Min Act: -0.1700
Data Index: 2102145 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5874. Min Range: -6.5874
Max Act: 5.7749. Min Act: -0.1700
Data Index: 7265401 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5874. Min Range: -6.5874
Max Act: 5.7749. Min Act: -0.1700
Data Index: 1630230 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5874. Min Range: -6.5874
Max Act: 5.7437. Min Act: -0.1700
Data Index: 470393 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5874. Min Range: -6.5874
Max Act: 5.7124. Min Act: -0.1700
Data Index: 4544772 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5874. Min Range: -6.5874
Max Act: 5.7124. Min Act: -0.1700
Data Index: 6018175 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5874. Min Range: -6.5874
Max Act: 5.7124. Min Act: -0.1700
Data Index: 6266390 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5874. Min Range: -6.5874
Max Act: 5.7124. Min Act: -0.1700
Data Index: 7327979 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5874. Min Range: -6.5874
Max Act: 5.7124. Min Act: -0.1700
Data Index: 568406 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5874. Min Range: -6.5874
Max Act: 5.6812. Min Act: -0.1700
Data Index: 3423310 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5874. Min Range: -6.5874
Max Act: 5.6499. Min Act: -0.1700
Data Index: 557663 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19