Model: None
Dataset: The Pile
Neuron 1358 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 10.6803. Min Range: -10.6803
Max Act: 10.6803. Min Act: -0.1699
Data Index: 8150486 (The Pile)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6803. Min Range: -10.6803
Max Act: 10.6178. Min Act: -0.1700
Data Index: 1996264 (The Pile)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6803. Min Range: -10.6803
Max Act: 10.6178. Min Act: -0.1639
Data Index: 148324 (The Pile)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6803. Min Range: -10.6803
Max Act: 10.6178. Min Act: -0.1700
Data Index: 3929952 (The Pile)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6803. Min Range: -10.6803
Max Act: 10.6178. Min Act: -0.1699
Data Index: 1136480 (The Pile)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6803. Min Range: -10.6803
Max Act: 10.6178. Min Act: -0.1700
Data Index: 10251907 (The Pile)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6803. Min Range: -10.6803
Max Act: 10.6178. Min Act: -0.1689
Data Index: 6397989 (The Pile)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6803. Min Range: -10.6803
Max Act: 10.5553. Min Act: -0.1700
Data Index: 1218423 (The Pile)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6803. Min Range: -10.6803
Max Act: 10.5553. Min Act: -0.1697
Data Index: 1321610 (The Pile)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6803. Min Range: -10.6803
Max Act: 10.5553. Min Act: -0.1683
Data Index: 1648076 (The Pile)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6803. Min Range: -10.6803
Max Act: 10.5553. Min Act: -0.1696
Data Index: 3086555 (The Pile)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6803. Min Range: -10.6803
Max Act: 10.5553. Min Act: -0.1700
Data Index: 9170715 (The Pile)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6803. Min Range: -10.6803
Max Act: 10.5553. Min Act: -0.1683
Data Index: 5799122 (The Pile)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6803. Min Range: -10.6803
Max Act: 10.4928. Min Act: -0.1700
Data Index: 2441305 (The Pile)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6803. Min Range: -10.6803
Max Act: 10.4928. Min Act: -0.1700
Data Index: 8235500 (The Pile)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6803. Min Range: -10.6803
Max Act: 10.4928. Min Act: -0.1698
Data Index: 2566730 (The Pile)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6803. Min Range: -10.6803
Max Act: 10.4928. Min Act: -0.1687
Data Index: 10334346 (The Pile)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6803. Min Range: -10.6803
Max Act: 10.4928. Min Act: -0.1700
Data Index: 9959905 (The Pile)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6803. Min Range: -10.6803
Max Act: 10.4928. Min Act: -0.1699
Data Index: 288174 (The Pile)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6803. Min Range: -10.6803
Max Act: 10.4928. Min Act: -0.0819
Data Index: 8324758 (The Pile)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19