Model: None
Dataset: The Pile
Neuron 2510 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.7086. Min Act: -0.1700
Data Index: 7540419 (The Pile)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.6460. Min Act: -0.1700
Data Index: 5041716 (The Pile)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.6304. Min Act: -0.1700
Data Index: 4826975 (The Pile)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.6147. Min Act: -0.1700
Data Index: 10292803 (The Pile)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.6147. Min Act: -0.1700
Data Index: 4292385 (The Pile)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.5991. Min Act: -0.1700
Data Index: 6843842 (The Pile)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.5991. Min Act: -0.1700
Data Index: 2247652 (The Pile)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.5834. Min Act: -0.1700
Data Index: 7414341 (The Pile)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.5521. Min Act: -0.1700
Data Index: 3895147 (The Pile)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.5521. Min Act: -0.1700
Data Index: 7422959 (The Pile)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.5521. Min Act: -0.1700
Data Index: 9623998 (The Pile)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.5364. Min Act: -0.1700
Data Index: 6537213 (The Pile)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.5364. Min Act: -0.1700
Data Index: 4612841 (The Pile)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.5364. Min Act: -0.1700
Data Index: 5499921 (The Pile)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.5208. Min Act: -0.1700
Data Index: 3565981 (The Pile)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.5208. Min Act: -0.1700
Data Index: 4449479 (The Pile)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.5208. Min Act: -0.1700
Data Index: 5732312 (The Pile)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.5051. Min Act: -0.1700
Data Index: 2438254 (The Pile)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.5051. Min Act: -0.1700
Data Index: 1843969 (The Pile)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.4894. Min Act: -0.1700
Data Index: 7680287 (The Pile)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #19