Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5662 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7222. Min Range: -5.7222
Max Act: 5.7222. Min Act: -0.1700
Data Index: 841967 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7222. Min Range: -5.7222
Max Act: 5.6910. Min Act: -0.1700
Data Index: 4101275 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7222. Min Range: -5.7222
Max Act: 5.4722. Min Act: -0.1700
Data Index: 8747465 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7222. Min Range: -5.7222
Max Act: 5.4410. Min Act: -0.1700
Data Index: 4280040 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7222. Min Range: -5.7222
Max Act: 5.4410. Min Act: -0.1700
Data Index: 6866150 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7222. Min Range: -5.7222
Max Act: 5.4097. Min Act: -0.1700
Data Index: 2853302 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7222. Min Range: -5.7222
Max Act: 5.4410. Min Act: -0.1700
Data Index: 3837016 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7222. Min Range: -5.7222
Max Act: 5.3785. Min Act: -0.1700
Data Index: 8326621 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7222. Min Range: -5.7222
Max Act: 5.3785. Min Act: -0.1700
Data Index: 1390456 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7222. Min Range: -5.7222
Max Act: 5.3472. Min Act: -0.1700
Data Index: 3200854 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7222. Min Range: -5.7222
Max Act: 5.3472. Min Act: -0.1700
Data Index: 7444648 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7222. Min Range: -5.7222
Max Act: 5.3472. Min Act: -0.1700
Data Index: 7174926 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7222. Min Range: -5.7222
Max Act: 5.3472. Min Act: -0.1700
Data Index: 7996560 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7222. Min Range: -5.7222
Max Act: 5.3472. Min Act: -0.1700
Data Index: 3593760 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7222. Min Range: -5.7222
Max Act: 5.3160. Min Act: -0.1700
Data Index: 1469183 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7222. Min Range: -5.7222
Max Act: 5.3160. Min Act: -0.1700
Data Index: 5317206 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7222. Min Range: -5.7222
Max Act: 5.3160. Min Act: -0.1700
Data Index: 4395034 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7222. Min Range: -5.7222
Max Act: 5.2847. Min Act: -0.1700
Data Index: 188575 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7222. Min Range: -5.7222
Max Act: 5.2847. Min Act: -0.1700
Data Index: 1268045 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7222. Min Range: -5.7222
Max Act: 5.2535. Min Act: -0.1700
Data Index: 2319937 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19