Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 270 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.8176. Min Act: -0.1700
Data Index: 638159 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.5051. Min Act: -0.1700
Data Index: 1665318 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.4426. Min Act: -0.1700
Data Index: 7385027 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.4113. Min Act: -0.1700
Data Index: 5535513 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.4426. Min Act: -0.1700
Data Index: 1156957 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.3801. Min Act: -0.1700
Data Index: 4037790 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.3176. Min Act: -0.1700
Data Index: 7242987 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.3176. Min Act: -0.1700
Data Index: 5251726 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.2551. Min Act: -0.1700
Data Index: 8548300 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.2551. Min Act: -0.1700
Data Index: 4972967 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.2238. Min Act: -0.1700
Data Index: 695333 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.1926. Min Act: -0.1700
Data Index: 2587240 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.1926. Min Act: -0.1700
Data Index: 4637346 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.1301. Min Act: -0.1700
Data Index: 1736198 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.1301. Min Act: -0.1700
Data Index: 6733221 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.0988. Min Act: -0.1700
Data Index: 2245111 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.0988. Min Act: -0.1700
Data Index: 3170839 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.0676. Min Act: -0.1700
Data Index: 7440281 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.0676. Min Act: -0.1700
Data Index: 6053387 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.0676. Min Act: -0.1700
Data Index: 5758127 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19