Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3067 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2410. Min Range: -6.2410
Max Act: 6.2410. Min Act: -0.1700
Data Index: 1667660 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2410. Min Range: -6.2410
Max Act: 6.2410. Min Act: -0.1700
Data Index: 5858444 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2410. Min Range: -6.2410
Max Act: 6.2097. Min Act: -0.1700
Data Index: 2610655 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2410. Min Range: -6.2410
Max Act: 6.1472. Min Act: -0.1700
Data Index: 1438272 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2410. Min Range: -6.2410
Max Act: 6.1160. Min Act: -0.1700
Data Index: 6191402 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2410. Min Range: -6.2410
Max Act: 6.0847. Min Act: -0.1700
Data Index: 1123623 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2410. Min Range: -6.2410
Max Act: 6.0847. Min Act: -0.1700
Data Index: 1176651 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2410. Min Range: -6.2410
Max Act: 6.1160. Min Act: -0.1700
Data Index: 7004963 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2410. Min Range: -6.2410
Max Act: 6.1160. Min Act: -0.1700
Data Index: 6729939 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2410. Min Range: -6.2410
Max Act: 6.0847. Min Act: -0.1700
Data Index: 6021611 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2410. Min Range: -6.2410
Max Act: 6.0535. Min Act: -0.1700
Data Index: 796402 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2410. Min Range: -6.2410
Max Act: 6.0535. Min Act: -0.1700
Data Index: 7778981 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2410. Min Range: -6.2410
Max Act: 6.0535. Min Act: -0.1700
Data Index: 6462267 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2410. Min Range: -6.2410
Max Act: 6.0847. Min Act: -0.1700
Data Index: 3492654 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2410. Min Range: -6.2410
Max Act: 6.0222. Min Act: -0.1700
Data Index: 1604909 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2410. Min Range: -6.2410
Max Act: 5.9910. Min Act: -0.1700
Data Index: 5266229 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2410. Min Range: -6.2410
Max Act: 5.9910. Min Act: -0.1700
Data Index: 3296584 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2410. Min Range: -6.2410
Max Act: 5.9910. Min Act: -0.1700
Data Index: 2622942 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2410. Min Range: -6.2410
Max Act: 5.9597. Min Act: -0.1700
Data Index: 1593445 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2410. Min Range: -6.2410
Max Act: 5.9285. Min Act: -0.1700
Data Index: 6515507 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19