Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4451 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9638. Min Range: -6.9638
Max Act: 6.9638. Min Act: -0.1700
Data Index: 4443952 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9638. Min Range: -6.9638
Max Act: 6.9638. Min Act: -0.1700
Data Index: 5212862 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9638. Min Range: -6.9638
Max Act: 6.9326. Min Act: -0.1700
Data Index: 3613607 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9638. Min Range: -6.9638
Max Act: 6.9326. Min Act: -0.1700
Data Index: 6257 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9638. Min Range: -6.9638
Max Act: 6.8701. Min Act: -0.1700
Data Index: 163668 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9638. Min Range: -6.9638
Max Act: 6.8076. Min Act: -0.1700
Data Index: 1283410 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9638. Min Range: -6.9638
Max Act: 6.7138. Min Act: -0.1700
Data Index: 2457349 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9638. Min Range: -6.9638
Max Act: 6.7451. Min Act: -0.1700
Data Index: 2624306 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9638. Min Range: -6.9638
Max Act: 6.7138. Min Act: -0.1700
Data Index: 2353526 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9638. Min Range: -6.9638
Max Act: 6.7138. Min Act: -0.1700
Data Index: 1041195 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9638. Min Range: -6.9638
Max Act: 6.6513. Min Act: -0.1700
Data Index: 2433464 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9638. Min Range: -6.9638
Max Act: 6.6513. Min Act: -0.1700
Data Index: 4840732 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9638. Min Range: -6.9638
Max Act: 6.5888. Min Act: -0.1700
Data Index: 8723273 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9638. Min Range: -6.9638
Max Act: 6.5888. Min Act: -0.1700
Data Index: 8045889 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9638. Min Range: -6.9638
Max Act: 6.5888. Min Act: -0.1700
Data Index: 7316163 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9638. Min Range: -6.9638
Max Act: 6.5888. Min Act: -0.1700
Data Index: 7145653 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9638. Min Range: -6.9638
Max Act: 6.5576. Min Act: -0.1700
Data Index: 3857000 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9638. Min Range: -6.9638
Max Act: 6.5576. Min Act: -0.1700
Data Index: 4780114 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9638. Min Range: -6.9638
Max Act: 6.5576. Min Act: -0.1700
Data Index: 7005829 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9638. Min Range: -6.9638
Max Act: 6.5888. Min Act: -0.1700
Data Index: 44737 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #19