Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2908 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.4905. Min Act: -0.1700
Data Index: 5514249 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.2718. Min Act: -0.1700
Data Index: 8430403 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.2405. Min Act: -0.1700
Data Index: 847343 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.2093. Min Act: -0.1700
Data Index: 5514250 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.2093. Min Act: -0.1700
Data Index: 2676481 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.2093. Min Act: -0.1700
Data Index: 13731 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.1780. Min Act: -0.1700
Data Index: 2588979 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.1780. Min Act: -0.1700
Data Index: 149992 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.1155. Min Act: -0.1700
Data Index: 4067070 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.0843. Min Act: -0.1700
Data Index: 6633197 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.0843. Min Act: -0.1700
Data Index: 6567916 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.0530. Min Act: -0.1700
Data Index: 7992942 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.0218. Min Act: -0.1700
Data Index: 2043098 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.0218. Min Act: -0.1700
Data Index: 7631983 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4905. Min Range: -5.4905
Max Act: 4.9905. Min Act: -0.1700
Data Index: 7726312 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4905. Min Range: -5.4905
Max Act: 4.9593. Min Act: -0.1700
Data Index: 1262663 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4905. Min Range: -5.4905
Max Act: 4.9593. Min Act: -0.1700
Data Index: 4359808 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4905. Min Range: -5.4905
Max Act: 4.9593. Min Act: -0.1700
Data Index: 3810351 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4905. Min Range: -5.4905
Max Act: 4.9593. Min Act: -0.1700
Data Index: 4138511 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4905. Min Range: -5.4905
Max Act: 4.9593. Min Act: -0.1700
Data Index: 2168234 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19