Model: None
Dataset: The Pile
Neuron 772 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 3.9442. Min Range: -3.9442
Max Act: 3.9442. Min Act: -0.1700
Data Index: 4268160 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9442. Min Range: -3.9442
Max Act: 3.9442. Min Act: -0.1700
Data Index: 1272434 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9442. Min Range: -3.9442
Max Act: 3.8191. Min Act: -0.1700
Data Index: 1945991 (The Pile)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9442. Min Range: -3.9442
Max Act: 3.8191. Min Act: -0.1700
Data Index: 414013 (The Pile)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9442. Min Range: -3.9442
Max Act: 3.8191. Min Act: -0.1700
Data Index: 8902634 (The Pile)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9442. Min Range: -3.9442
Max Act: 3.7878. Min Act: -0.1700
Data Index: 8131581 (The Pile)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9442. Min Range: -3.9442
Max Act: 3.7565. Min Act: -0.1700
Data Index: 5945105 (The Pile)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9442. Min Range: -3.9442
Max Act: 3.7409. Min Act: -0.1700
Data Index: 5815146 (The Pile)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9442. Min Range: -3.9442
Max Act: 3.7252. Min Act: -0.1700
Data Index: 5139965 (The Pile)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9442. Min Range: -3.9442
Max Act: 3.7252. Min Act: -0.1700
Data Index: 4915217 (The Pile)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9442. Min Range: -3.9442
Max Act: 3.7096. Min Act: -0.1700
Data Index: 1477613 (The Pile)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9442. Min Range: -3.9442
Max Act: 3.7252. Min Act: -0.1700
Data Index: 1403021 (The Pile)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9442. Min Range: -3.9442
Max Act: 3.6939. Min Act: -0.1700
Data Index: 7906143 (The Pile)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9442. Min Range: -3.9442
Max Act: 3.6470. Min Act: -0.1700
Data Index: 6475972 (The Pile)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9442. Min Range: -3.9442
Max Act: 3.6783. Min Act: -0.1700
Data Index: 9293357 (The Pile)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9442. Min Range: -3.9442
Max Act: 3.6783. Min Act: -0.1700
Data Index: 8401715 (The Pile)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9442. Min Range: -3.9442
Max Act: 3.6626. Min Act: -0.1700
Data Index: 4373681 (The Pile)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9442. Min Range: -3.9442
Max Act: 3.6783. Min Act: -0.1700
Data Index: 7190184 (The Pile)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9442. Min Range: -3.9442
Max Act: 3.6783. Min Act: -0.1700
Data Index: 6541343 (The Pile)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9442. Min Range: -3.9442
Max Act: 3.6626. Min Act: -0.1700
Data Index: 8170850 (The Pile)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19