Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 193 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.7923. Min Act: -0.1700
Data Index: 2685128 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.7610. Min Act: -0.1700
Data Index: 20320 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.6673. Min Act: -0.1700
Data Index: 7586070 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.6673. Min Act: -0.1700
Data Index: 2385693 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.6360. Min Act: -0.1700
Data Index: 5630763 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.6673. Min Act: -0.1700
Data Index: 5723265 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.6048. Min Act: -0.1700
Data Index: 3098023 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.6048. Min Act: -0.1700
Data Index: 6347667 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.6360. Min Act: -0.1700
Data Index: 7399712 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.6360. Min Act: -0.1700
Data Index: 8803130 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.6360. Min Act: -0.1700
Data Index: 3002232 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.6048. Min Act: -0.1700
Data Index: 3623748 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.6048. Min Act: -0.1700
Data Index: 1152885 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.5735. Min Act: -0.1700
Data Index: 8169183 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.5423. Min Act: -0.1700
Data Index: 6298143 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.5423. Min Act: -0.1700
Data Index: 4768769 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.5423. Min Act: -0.1700
Data Index: 8344159 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.5110. Min Act: -0.1700
Data Index: 3850136 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.5423. Min Act: -0.1700
Data Index: 7660990 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.4798. Min Act: -0.1700
Data Index: 7399714 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19