Model: None
Dataset: The Pile
Neuron 1525 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')
Text #0
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.2564. Min Act: -0.1700
Data Index: 4775209 (The Pile)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.2407. Min Act: -0.1700
Data Index: 390218 (The Pile)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.2250. Min Act: -0.1700
Data Index: 10642740 (The Pile)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.2093. Min Act: -0.1700
Data Index: 8493430 (The Pile)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.1935. Min Act: -0.1698
Data Index: 8607120 (The Pile)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.1778. Min Act: -0.1700
Data Index: 9175624 (The Pile)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.1778. Min Act: -0.1700
Data Index: 4995960 (The Pile)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.1621. Min Act: -0.1700
Data Index: 5960835 (The Pile)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.1463. Min Act: -0.1700
Data Index: 5987923 (The Pile)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.1148. Min Act: -0.1700
Data Index: 7428216 (The Pile)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.1148. Min Act: -0.1700
Data Index: 5626438 (The Pile)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.1148. Min Act: -0.1700
Data Index: 4910392 (The Pile)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.0990. Min Act: -0.1700
Data Index: 3816098 (The Pile)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.0990. Min Act: -0.1700
Data Index: 9228715 (The Pile)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.0990. Min Act: -0.1700
Data Index: 2321417 (The Pile)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.0833. Min Act: -0.1700
Data Index: 4627161 (The Pile)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.0675. Min Act: -0.1700
Data Index: 9129129 (The Pile)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.0675. Min Act: -0.1700
Data Index: 2317307 (The Pile)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.0675. Min Act: -0.1696
Data Index: 8453818 (The Pile)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.0675. Min Act: -0.1700
Data Index: 10369763 (The Pile)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19