Model: None
Dataset: The Pile
Neuron 681 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.7119. Min Range: -2.7119
Max Act: 2.7119. Min Act: -0.1700
Data Index: 6479120 (The Pile)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7119. Min Range: -2.7119
Max Act: 2.6959. Min Act: -0.1700
Data Index: 5020507 (The Pile)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7119. Min Range: -2.7119
Max Act: 2.5996. Min Act: -0.1700
Data Index: 10600892 (The Pile)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7119. Min Range: -2.7119
Max Act: 2.6157. Min Act: -0.1700
Data Index: 9585587 (The Pile)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7119. Min Range: -2.7119
Max Act: 2.5512. Min Act: -0.1700
Data Index: 8461644 (The Pile)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7119. Min Range: -2.7119
Max Act: 2.5351. Min Act: -0.1700
Data Index: 4833162 (The Pile)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7119. Min Range: -2.7119
Max Act: 2.5512. Min Act: -0.1700
Data Index: 8473542 (The Pile)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7119. Min Range: -2.7119
Max Act: 2.5996. Min Act: -0.1700
Data Index: 5176947 (The Pile)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7119. Min Range: -2.7119
Max Act: 2.5351. Min Act: -0.1700
Data Index: 91046 (The Pile)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7119. Min Range: -2.7119
Max Act: 2.5027. Min Act: -0.1700
Data Index: 1995879 (The Pile)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7119. Min Range: -2.7119
Max Act: 2.5027. Min Act: -0.1699
Data Index: 2191181 (The Pile)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7119. Min Range: -2.7119
Max Act: 2.5189. Min Act: -0.1700
Data Index: 7203020 (The Pile)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7119. Min Range: -2.7119
Max Act: 2.5027. Min Act: -0.1700
Data Index: 7644177 (The Pile)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7119. Min Range: -2.7119
Max Act: 2.4865. Min Act: -0.1700
Data Index: 7146410 (The Pile)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7119. Min Range: -2.7119
Max Act: 2.4541. Min Act: -0.1700
Data Index: 6622167 (The Pile)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7119. Min Range: -2.7119
Max Act: 2.5027. Min Act: -0.1700
Data Index: 1652362 (The Pile)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7119. Min Range: -2.7119
Max Act: 2.4865. Min Act: -0.1700
Data Index: 1587854 (The Pile)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7119. Min Range: -2.7119
Max Act: 2.5189. Min Act: -0.1700
Data Index: 1082848 (The Pile)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7119. Min Range: -2.7119
Max Act: 2.5027. Min Act: -0.1700
Data Index: 424430 (The Pile)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7119. Min Range: -2.7119
Max Act: 2.4865. Min Act: -0.1700
Data Index: 2572861 (The Pile)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19