Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 842 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0776. Min Range: -3.0776
Max Act: 3.0776. Min Act: -0.1700
Data Index: 6366254 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0776. Min Range: -3.0776
Max Act: 3.0618. Min Act: -0.1700
Data Index: 3441913 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0776. Min Range: -3.0776
Max Act: 2.9828. Min Act: -0.1700
Data Index: 3413361 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0776. Min Range: -3.0776
Max Act: 2.9828. Min Act: -0.1700
Data Index: 5659115 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0776. Min Range: -3.0776
Max Act: 2.9828. Min Act: -0.1700
Data Index: 3382551 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0776. Min Range: -3.0776
Max Act: 2.9354. Min Act: -0.1700
Data Index: 6113357 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0776. Min Range: -3.0776
Max Act: 2.9037. Min Act: -0.1700
Data Index: 6832501 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0776. Min Range: -3.0776
Max Act: 2.8878. Min Act: -0.1700
Data Index: 8029871 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0776. Min Range: -3.0776
Max Act: 2.8878. Min Act: -0.1700
Data Index: 3999497 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0776. Min Range: -3.0776
Max Act: 2.9195. Min Act: -0.1700
Data Index: 1343354 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0776. Min Range: -3.0776
Max Act: 2.9037. Min Act: -0.1700
Data Index: 2885064 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0776. Min Range: -3.0776
Max Act: 2.8402. Min Act: -0.1700
Data Index: 7119430 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0776. Min Range: -3.0776
Max Act: 2.8561. Min Act: -0.1700
Data Index: 6945716 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0776. Min Range: -3.0776
Max Act: 2.9037. Min Act: -0.1700
Data Index: 2910245 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0776. Min Range: -3.0776
Max Act: 2.8719. Min Act: -0.1700
Data Index: 7013982 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0776. Min Range: -3.0776
Max Act: 2.8402. Min Act: -0.1700
Data Index: 338202 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0776. Min Range: -3.0776
Max Act: 2.8719. Min Act: -0.1700
Data Index: 2814951 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0776. Min Range: -3.0776
Max Act: 2.8719. Min Act: -0.1700
Data Index: 1917535 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0776. Min Range: -3.0776
Max Act: 2.8878. Min Act: -0.1700
Data Index: 3553300 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0776. Min Range: -3.0776
Max Act: 2.8402. Min Act: -0.1700
Data Index: 53578 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19