Model: None
Dataset: The Pile
Neuron 977 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.7509. Min Act: -0.1700
Data Index: 8898501 (The Pile)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.7509. Min Act: -0.1700
Data Index: 5289123 (The Pile)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.7353. Min Act: -0.1700
Data Index: 47122 (The Pile)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.7196. Min Act: -0.1700
Data Index: 6049245 (The Pile)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.7196. Min Act: -0.1700
Data Index: 3517624 (The Pile)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.7040. Min Act: -0.1700
Data Index: 9026820 (The Pile)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.7040. Min Act: -0.1700
Data Index: 4099323 (The Pile)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.7040. Min Act: -0.1700
Data Index: 10611245 (The Pile)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6883. Min Act: -0.1700
Data Index: 3170258 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6883. Min Act: -0.1700
Data Index: 8643318 (The Pile)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6883. Min Act: -0.1700
Data Index: 8878163 (The Pile)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6883. Min Act: -0.1700
Data Index: 2872977 (The Pile)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6570. Min Act: -0.1700
Data Index: 5988739 (The Pile)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6570. Min Act: -0.1700
Data Index: 6674732 (The Pile)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6414. Min Act: -0.1700
Data Index: 4898533 (The Pile)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6414. Min Act: -0.1700
Data Index: 719160 (The Pile)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6414. Min Act: -0.1700
Data Index: 1189503 (The Pile)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6414. Min Act: -0.1700
Data Index: 5762129 (The Pile)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6257. Min Act: -0.1700
Data Index: 2264480 (The Pile)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6257. Min Act: -0.1700
Data Index: 7741262 (The Pile)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19