Model: None
Dataset: The Pile
Neuron 638 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.4983. Min Range: -3.4983
Max Act: 3.4983. Min Act: -0.1700
Data Index: 3518933 (The Pile)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4983. Min Range: -3.4983
Max Act: 3.4669. Min Act: -0.1700
Data Index: 8502615 (The Pile)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4983. Min Range: -3.4983
Max Act: 3.4669. Min Act: -0.1700
Data Index: 9845210 (The Pile)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4983. Min Range: -3.4983
Max Act: 3.4513. Min Act: -0.1700
Data Index: 4173999 (The Pile)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4983. Min Range: -3.4983
Max Act: 3.4199. Min Act: -0.1700
Data Index: 1380078 (The Pile)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4983. Min Range: -3.4983
Max Act: 3.4042. Min Act: -0.1700
Data Index: 3289745 (The Pile)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4983. Min Range: -3.4983
Max Act: 3.3729. Min Act: -0.1700
Data Index: 8736919 (The Pile)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4983. Min Range: -3.4983
Max Act: 3.3729. Min Act: -0.1700
Data Index: 10142589 (The Pile)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4983. Min Range: -3.4983
Max Act: 3.3729. Min Act: -0.1700
Data Index: 1513995 (The Pile)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4983. Min Range: -3.4983
Max Act: 3.3729. Min Act: -0.1700
Data Index: 10757717 (The Pile)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4983. Min Range: -3.4983
Max Act: 3.3729. Min Act: -0.1700
Data Index: 7522784 (The Pile)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4983. Min Range: -3.4983
Max Act: 3.3572. Min Act: -0.1700
Data Index: 9442421 (The Pile)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4983. Min Range: -3.4983
Max Act: 3.3258. Min Act: -0.1700
Data Index: 6803830 (The Pile)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4983. Min Range: -3.4983
Max Act: 3.3258. Min Act: -0.1700
Data Index: 6882253 (The Pile)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4983. Min Range: -3.4983
Max Act: 3.3258. Min Act: -0.1700
Data Index: 2270269 (The Pile)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4983. Min Range: -3.4983
Max Act: 3.3101. Min Act: -0.1700
Data Index: 2039075 (The Pile)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4983. Min Range: -3.4983
Max Act: 3.3101. Min Act: -0.1700
Data Index: 9409471 (The Pile)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4983. Min Range: -3.4983
Max Act: 3.2944. Min Act: -0.1700
Data Index: 639310 (The Pile)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4983. Min Range: -3.4983
Max Act: 3.2944. Min Act: -0.1700
Data Index: 2003489 (The Pile)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4983. Min Range: -3.4983
Max Act: 3.2787. Min Act: -0.1700
Data Index: 3826058 (The Pile)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19