Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 951 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2051. Min Range: -7.2051
Max Act: 7.2051. Min Act: -0.1700
Data Index: 1979701 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2051. Min Range: -7.2051
Max Act: 6.9551. Min Act: -0.1700
Data Index: 1785313 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2051. Min Range: -7.2051
Max Act: 6.6738. Min Act: -0.1700
Data Index: 2523302 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2051. Min Range: -7.2051
Max Act: 6.5801. Min Act: -0.1700
Data Index: 7553959 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2051. Min Range: -7.2051
Max Act: 6.6113. Min Act: -0.1700
Data Index: 3716042 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2051. Min Range: -7.2051
Max Act: 6.5176. Min Act: -0.1700
Data Index: 4343832 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2051. Min Range: -7.2051
Max Act: 6.3926. Min Act: -0.1700
Data Index: 4837543 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2051. Min Range: -7.2051
Max Act: 6.3613. Min Act: -0.1700
Data Index: 4560705 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2051. Min Range: -7.2051
Max Act: 6.3613. Min Act: -0.1700
Data Index: 4461309 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2051. Min Range: -7.2051
Max Act: 6.2988. Min Act: -0.1700
Data Index: 1378179 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2051. Min Range: -7.2051
Max Act: 6.2988. Min Act: -0.1700
Data Index: 8206173 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2051. Min Range: -7.2051
Max Act: 6.2988. Min Act: -0.1700
Data Index: 8213728 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2051. Min Range: -7.2051
Max Act: 6.2988. Min Act: -0.1700
Data Index: 4335220 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2051. Min Range: -7.2051
Max Act: 6.2676. Min Act: -0.1700
Data Index: 4961588 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2051. Min Range: -7.2051
Max Act: 6.2676. Min Act: -0.1700
Data Index: 5904998 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2051. Min Range: -7.2051
Max Act: 6.2676. Min Act: -0.1700
Data Index: 309336 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2051. Min Range: -7.2051
Max Act: 6.2676. Min Act: -0.1700
Data Index: 100866 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2051. Min Range: -7.2051
Max Act: 6.2676. Min Act: -0.1700
Data Index: 5800943 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2051. Min Range: -7.2051
Max Act: 6.2363. Min Act: -0.1700
Data Index: 5946724 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2051. Min Range: -7.2051
Max Act: 6.2051. Min Act: -0.1700
Data Index: 269711 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19