Model: None
Dataset: The Pile
Neuron 1017 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.1240. Min Range: -2.1240
Max Act: 2.1240. Min Act: -0.1700
Data Index: 10659120 (The Pile)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1240. Min Range: -2.1240
Max Act: 2.1240. Min Act: -0.1700
Data Index: 562279 (The Pile)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1240. Min Range: -2.1240
Max Act: 2.1073. Min Act: -0.1700
Data Index: 7393479 (The Pile)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1240. Min Range: -2.1240
Max Act: 2.0906. Min Act: -0.1700
Data Index: 9075076 (The Pile)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1240. Min Range: -2.1240
Max Act: 2.0906. Min Act: -0.1700
Data Index: 3515756 (The Pile)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1240. Min Range: -2.1240
Max Act: 2.1073. Min Act: -0.1700
Data Index: 3535048 (The Pile)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1240. Min Range: -2.1240
Max Act: 2.0906. Min Act: -0.1700
Data Index: 5233101 (The Pile)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1240. Min Range: -2.1240
Max Act: 2.0906. Min Act: -0.1700
Data Index: 1452824 (The Pile)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1240. Min Range: -2.1240
Max Act: 2.0906. Min Act: -0.1700
Data Index: 6775810 (The Pile)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1240. Min Range: -2.1240
Max Act: 2.0402. Min Act: -0.1700
Data Index: 6764362 (The Pile)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1240. Min Range: -2.1240
Max Act: 2.0738. Min Act: -0.1700
Data Index: 10751916 (The Pile)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1240. Min Range: -2.1240
Max Act: 2.0570. Min Act: -0.1700
Data Index: 7360362 (The Pile)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1240. Min Range: -2.1240
Max Act: 2.0738. Min Act: -0.1700
Data Index: 478075 (The Pile)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1240. Min Range: -2.1240
Max Act: 2.0738. Min Act: -0.1700
Data Index: 9206576 (The Pile)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1240. Min Range: -2.1240
Max Act: 2.0570. Min Act: -0.1700
Data Index: 563526 (The Pile)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1240. Min Range: -2.1240
Max Act: 2.0570. Min Act: -0.1700
Data Index: 4465046 (The Pile)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1240. Min Range: -2.1240
Max Act: 2.0738. Min Act: -0.1700
Data Index: 5566523 (The Pile)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1240. Min Range: -2.1240
Max Act: 2.0570. Min Act: -0.1700
Data Index: 7067618 (The Pile)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1240. Min Range: -2.1240
Max Act: 2.0570. Min Act: -0.1700
Data Index: 443959 (The Pile)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1240. Min Range: -2.1240
Max Act: 2.0234. Min Act: -0.1700
Data Index: 2350345 (The Pile)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19