Model: None
Dataset: The Pile
Neuron 1542 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 3.1246. Min Range: -3.1246
Max Act: 3.1246. Min Act: -0.1700
Data Index: 4745610 (The Pile)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1246. Min Range: -3.1246
Max Act: 3.0615. Min Act: -0.1700
Data Index: 5468096 (The Pile)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1246. Min Range: -3.1246
Max Act: 3.0615. Min Act: -0.1700
Data Index: 3196541 (The Pile)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1246. Min Range: -3.1246
Max Act: 3.0141. Min Act: -0.1700
Data Index: 8460710 (The Pile)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1246. Min Range: -3.1246
Max Act: 2.9983. Min Act: -0.1700
Data Index: 4092827 (The Pile)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1246. Min Range: -3.1246
Max Act: 3.0141. Min Act: -0.1700
Data Index: 2841910 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1246. Min Range: -3.1246
Max Act: 2.9983. Min Act: -0.1700
Data Index: 6799588 (The Pile)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1246. Min Range: -3.1246
Max Act: 2.9983. Min Act: -0.1700
Data Index: 2975289 (The Pile)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1246. Min Range: -3.1246
Max Act: 2.9667. Min Act: -0.1700
Data Index: 1623122 (The Pile)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1246. Min Range: -3.1246
Max Act: 2.9825. Min Act: -0.1700
Data Index: 2106879 (The Pile)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1246. Min Range: -3.1246
Max Act: 2.9825. Min Act: -0.1700
Data Index: 5577896 (The Pile)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1246. Min Range: -3.1246
Max Act: 2.9983. Min Act: -0.1700
Data Index: 1634842 (The Pile)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1246. Min Range: -3.1246
Max Act: 2.9509. Min Act: -0.1700
Data Index: 88828 (The Pile)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1246. Min Range: -3.1246
Max Act: 2.9667. Min Act: -0.1700
Data Index: 1595123 (The Pile)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1246. Min Range: -3.1246
Max Act: 2.9667. Min Act: -0.1700
Data Index: 551364 (The Pile)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1246. Min Range: -3.1246
Max Act: 2.9667. Min Act: -0.1700
Data Index: 3345905 (The Pile)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1246. Min Range: -3.1246
Max Act: 2.9667. Min Act: -0.1700
Data Index: 792829 (The Pile)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1246. Min Range: -3.1246
Max Act: 2.9667. Min Act: -0.1700
Data Index: 5109203 (The Pile)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1246. Min Range: -3.1246
Max Act: 2.9825. Min Act: -0.1700
Data Index: 7108325 (The Pile)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1246. Min Range: -3.1246
Max Act: 2.9667. Min Act: -0.1700
Data Index: 1750306 (The Pile)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19