Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4552 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3913. Min Range: -6.3913
Max Act: 6.3913. Min Act: -0.1700
Data Index: 2577511 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3913. Min Range: -6.3913
Max Act: 6.3600. Min Act: -0.1700
Data Index: 2928137 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3913. Min Range: -6.3913
Max Act: 6.3288. Min Act: -0.1700
Data Index: 2577521 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3913. Min Range: -6.3913
Max Act: 6.2975. Min Act: -0.1700
Data Index: 2066677 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3913. Min Range: -6.3913
Max Act: 6.2038. Min Act: -0.1700
Data Index: 6399608 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3913. Min Range: -6.3913
Max Act: 6.2038. Min Act: -0.1700
Data Index: 8423110 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3913. Min Range: -6.3913
Max Act: 6.2038. Min Act: -0.1700
Data Index: 5346408 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3913. Min Range: -6.3913
Max Act: 6.1725. Min Act: -0.1700
Data Index: 6399613 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3913. Min Range: -6.3913
Max Act: 6.1725. Min Act: -0.1700
Data Index: 8523373 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3913. Min Range: -6.3913
Max Act: 6.2038. Min Act: -0.1700
Data Index: 4922817 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3913. Min Range: -6.3913
Max Act: 6.1413. Min Act: -0.1700
Data Index: 5346409 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3913. Min Range: -6.3913
Max Act: 6.1413. Min Act: -0.1700
Data Index: 2813626 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3913. Min Range: -6.3913
Max Act: 6.1413. Min Act: -0.1700
Data Index: 1203978 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3913. Min Range: -6.3913
Max Act: 6.0788. Min Act: -0.1700
Data Index: 2198095 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3913. Min Range: -6.3913
Max Act: 6.1100. Min Act: -0.1700
Data Index: 4659141 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3913. Min Range: -6.3913
Max Act: 6.0788. Min Act: -0.1700
Data Index: 6460158 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3913. Min Range: -6.3913
Max Act: 6.0475. Min Act: -0.1700
Data Index: 1771098 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3913. Min Range: -6.3913
Max Act: 6.0475. Min Act: -0.1700
Data Index: 4772912 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3913. Min Range: -6.3913
Max Act: 6.0475. Min Act: -0.1700
Data Index: 1879966 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3913. Min Range: -6.3913
Max Act: 5.9850. Min Act: -0.1700
Data Index: 7156697 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19