Model: None
Dataset: The Pile
Neuron 970 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.5043. Min Range: -2.5043
Max Act: 2.5043. Min Act: -0.1700
Data Index: 4855327 (The Pile)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5043. Min Range: -2.5043
Max Act: 2.4719. Min Act: -0.1700
Data Index: 9309834 (The Pile)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5043. Min Range: -2.5043
Max Act: 2.4719. Min Act: -0.1700
Data Index: 3512280 (The Pile)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5043. Min Range: -2.5043
Max Act: 2.4557. Min Act: -0.1700
Data Index: 6861911 (The Pile)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5043. Min Range: -2.5043
Max Act: 2.4394. Min Act: -0.1700
Data Index: 4850605 (The Pile)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5043. Min Range: -2.5043
Max Act: 2.4231. Min Act: -0.1700
Data Index: 1578674 (The Pile)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5043. Min Range: -2.5043
Max Act: 2.4231. Min Act: -0.1700
Data Index: 2252451 (The Pile)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5043. Min Range: -2.5043
Max Act: 2.4394. Min Act: -0.1700
Data Index: 9076171 (The Pile)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5043. Min Range: -2.5043
Max Act: 2.4557. Min Act: -0.1699
Data Index: 3015019 (The Pile)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5043. Min Range: -2.5043
Max Act: 2.4231. Min Act: -0.1699
Data Index: 7583206 (The Pile)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5043. Min Range: -2.5043
Max Act: 2.4394. Min Act: -0.1700
Data Index: 9363288 (The Pile)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5043. Min Range: -2.5043
Max Act: 2.4394. Min Act: -0.1700
Data Index: 8364599 (The Pile)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5043. Min Range: -2.5043
Max Act: 2.4394. Min Act: -0.1700
Data Index: 3828459 (The Pile)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5043. Min Range: -2.5043
Max Act: 2.4394. Min Act: -0.1700
Data Index: 9487354 (The Pile)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5043. Min Range: -2.5043
Max Act: 2.4068. Min Act: -0.1700
Data Index: 2053897 (The Pile)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5043. Min Range: -2.5043
Max Act: 2.4394. Min Act: -0.1700
Data Index: 8262051 (The Pile)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5043. Min Range: -2.5043
Max Act: 2.4231. Min Act: -0.1700
Data Index: 323723 (The Pile)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5043. Min Range: -2.5043
Max Act: 2.4231. Min Act: -0.1700
Data Index: 5919989 (The Pile)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5043. Min Range: -2.5043
Max Act: 2.4231. Min Act: -0.1700
Data Index: 5624394 (The Pile)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5043. Min Range: -2.5043
Max Act: 2.4394. Min Act: -0.1700
Data Index: 10678439 (The Pile)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19