Model: None
Dataset: The Pile
Neuron 2007 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 1.6445. Min Range: -1.6445
Max Act: 1.6445. Min Act: -0.1700
Data Index: 977 (The Pile)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6445. Min Range: -1.6445
Max Act: 1.6445. Min Act: -0.1700
Data Index: 13560 (The Pile)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6445. Min Range: -1.6445
Max Act: 1.6445. Min Act: -0.1700
Data Index: 12547 (The Pile)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6445. Min Range: -1.6445
Max Act: 1.6445. Min Act: -0.1700
Data Index: 11921 (The Pile)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6445. Min Range: -1.6445
Max Act: 1.6445. Min Act: -0.1700
Data Index: 1331 (The Pile)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6445. Min Range: -1.6445
Max Act: 1.6445. Min Act: -0.1700
Data Index: 515 (The Pile)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6445. Min Range: -1.6445
Max Act: 1.6445. Min Act: -0.1700
Data Index: 16665 (The Pile)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6445. Min Range: -1.6445
Max Act: 1.6445. Min Act: -0.1700
Data Index: 2597 (The Pile)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6445. Min Range: -1.6445
Max Act: 1.6445. Min Act: -0.1700
Data Index: 2291 (The Pile)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6445. Min Range: -1.6445
Max Act: 1.6445. Min Act: -0.1700
Data Index: 9242 (The Pile)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6445. Min Range: -1.6445
Max Act: 1.6445. Min Act: -0.1700
Data Index: 14327 (The Pile)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6445. Min Range: -1.6445
Max Act: 1.6445. Min Act: -0.1700
Data Index: 1908 (The Pile)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6445. Min Range: -1.6445
Max Act: 1.6445. Min Act: -0.1700
Data Index: 8989 (The Pile)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6445. Min Range: -1.6445
Max Act: 1.6445. Min Act: -0.1700
Data Index: 16402 (The Pile)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6445. Min Range: -1.6445
Max Act: 1.6445. Min Act: -0.1700
Data Index: 7250 (The Pile)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6445. Min Range: -1.6445
Max Act: 1.6445. Min Act: -0.1700
Data Index: 6484 (The Pile)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6445. Min Range: -1.6445
Max Act: 1.6445. Min Act: -0.1700
Data Index: 15435 (The Pile)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6445. Min Range: -1.6445
Max Act: 1.6445. Min Act: -0.1700
Data Index: 5887 (The Pile)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6445. Min Range: -1.6445
Max Act: 1.6445. Min Act: -0.1700
Data Index: 5544 (The Pile)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6445. Min Range: -1.6445
Max Act: 1.6445. Min Act: -0.1700
Data Index: 15172 (The Pile)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19