Model: None
Dataset: The Pile
Neuron 874 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.7217. Min Range: -2.7217
Max Act: 2.7217. Min Act: -0.1700
Data Index: 174109 (The Pile)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7217. Min Range: -2.7217
Max Act: 2.6897. Min Act: -0.1700
Data Index: 8177421 (The Pile)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7217. Min Range: -2.7217
Max Act: 2.7057. Min Act: -0.1700
Data Index: 7251550 (The Pile)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7217. Min Range: -2.7217
Max Act: 2.6897. Min Act: -0.1700
Data Index: 6624350 (The Pile)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7217. Min Range: -2.7217
Max Act: 2.6576. Min Act: -0.1700
Data Index: 10632167 (The Pile)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7217. Min Range: -2.7217
Max Act: 2.6255. Min Act: -0.1700
Data Index: 6737270 (The Pile)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7217. Min Range: -2.7217
Max Act: 2.6416. Min Act: -0.1700
Data Index: 8984498 (The Pile)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7217. Min Range: -2.7217
Max Act: 2.6736. Min Act: -0.1700
Data Index: 1615317 (The Pile)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7217. Min Range: -2.7217
Max Act: 2.6576. Min Act: -0.1700
Data Index: 9938556 (The Pile)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7217. Min Range: -2.7217
Max Act: 2.6736. Min Act: -0.1700
Data Index: 8037962 (The Pile)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7217. Min Range: -2.7217
Max Act: 2.6576. Min Act: -0.1700
Data Index: 1006782 (The Pile)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7217. Min Range: -2.7217
Max Act: 2.6255. Min Act: -0.1700
Data Index: 8733844 (The Pile)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7217. Min Range: -2.7217
Max Act: 2.6255. Min Act: -0.1700
Data Index: 7781942 (The Pile)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7217. Min Range: -2.7217
Max Act: 2.6416. Min Act: -0.1700
Data Index: 8645461 (The Pile)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7217. Min Range: -2.7217
Max Act: 2.6416. Min Act: -0.1700
Data Index: 5721501 (The Pile)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7217. Min Range: -2.7217
Max Act: 2.6255. Min Act: -0.1700
Data Index: 3673953 (The Pile)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7217. Min Range: -2.7217
Max Act: 2.6094. Min Act: -0.1700
Data Index: 5153874 (The Pile)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7217. Min Range: -2.7217
Max Act: 2.6094. Min Act: -0.1700
Data Index: 7185027 (The Pile)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7217. Min Range: -2.7217
Max Act: 2.6094. Min Act: -0.1700
Data Index: 7977356 (The Pile)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7217. Min Range: -2.7217
Max Act: 2.5933. Min Act: -0.1700
Data Index: 7871833 (The Pile)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19