Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3803 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7482. Min Range: -4.7482
Max Act: 4.7482. Min Act: -0.1700
Data Index: 4324020 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7482. Min Range: -4.7482
Max Act: 4.6232. Min Act: -0.1700
Data Index: 2494409 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7482. Min Range: -4.7482
Max Act: 4.5920. Min Act: -0.1700
Data Index: 7339148 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7482. Min Range: -4.7482
Max Act: 4.5920. Min Act: -0.1700
Data Index: 340333 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7482. Min Range: -4.7482
Max Act: 4.5920. Min Act: -0.1700
Data Index: 5870617 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7482. Min Range: -4.7482
Max Act: 4.5607. Min Act: -0.1700
Data Index: 5384659 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7482. Min Range: -4.7482
Max Act: 4.5607. Min Act: -0.1700
Data Index: 8557819 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7482. Min Range: -4.7482
Max Act: 4.5295. Min Act: -0.1700
Data Index: 4989413 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7482. Min Range: -4.7482
Max Act: 4.5295. Min Act: -0.1700
Data Index: 3531902 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7482. Min Range: -4.7482
Max Act: 4.5295. Min Act: -0.1700
Data Index: 6304452 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7482. Min Range: -4.7482
Max Act: 4.5295. Min Act: -0.1700
Data Index: 5810267 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7482. Min Range: -4.7482
Max Act: 4.5295. Min Act: -0.1700
Data Index: 3147594 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7482. Min Range: -4.7482
Max Act: 4.4982. Min Act: -0.1700
Data Index: 8158956 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7482. Min Range: -4.7482
Max Act: 4.4982. Min Act: -0.1700
Data Index: 7780173 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7482. Min Range: -4.7482
Max Act: 4.4982. Min Act: -0.1700
Data Index: 7506091 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7482. Min Range: -4.7482
Max Act: 4.4670. Min Act: -0.1700
Data Index: 4043274 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7482. Min Range: -4.7482
Max Act: 4.4670. Min Act: -0.1700
Data Index: 8799626 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7482. Min Range: -4.7482
Max Act: 4.4357. Min Act: -0.1700
Data Index: 5852623 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7482. Min Range: -4.7482
Max Act: 4.4357. Min Act: -0.1700
Data Index: 1146180 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7482. Min Range: -4.7482
Max Act: 4.4357. Min Act: -0.1700
Data Index: 3778823 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19