Model: None
Dataset: The Pile
Neuron 1081 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 4.0565. Min Range: -4.0565
Max Act: 4.0565. Min Act: -0.1700
Data Index: 1164059 (The Pile)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0565. Min Range: -4.0565
Max Act: 4.0565. Min Act: -0.1700
Data Index: 10079605 (The Pile)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0565. Min Range: -4.0565
Max Act: 4.0252. Min Act: -0.1700
Data Index: 4824897 (The Pile)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0565. Min Range: -4.0565
Max Act: 3.9940. Min Act: -0.1700
Data Index: 1366440 (The Pile)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0565. Min Range: -4.0565
Max Act: 3.9940. Min Act: -0.1700
Data Index: 3948737 (The Pile)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0565. Min Range: -4.0565
Max Act: 3.9940. Min Act: -0.1700
Data Index: 9910113 (The Pile)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0565. Min Range: -4.0565
Max Act: 3.9314. Min Act: -0.1700
Data Index: 5745333 (The Pile)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0565. Min Range: -4.0565
Max Act: 3.9158. Min Act: -0.1700
Data Index: 1046368 (The Pile)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0565. Min Range: -4.0565
Max Act: 3.9158. Min Act: -0.1700
Data Index: 9246290 (The Pile)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0565. Min Range: -4.0565
Max Act: 3.9002. Min Act: -0.1700
Data Index: 5129228 (The Pile)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0565. Min Range: -4.0565
Max Act: 3.9002. Min Act: -0.1700
Data Index: 5158176 (The Pile)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0565. Min Range: -4.0565
Max Act: 3.8845. Min Act: -0.1700
Data Index: 8295055 (The Pile)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0565. Min Range: -4.0565
Max Act: 3.8689. Min Act: -0.1700
Data Index: 95029 (The Pile)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0565. Min Range: -4.0565
Max Act: 3.8376. Min Act: -0.1700
Data Index: 9317853 (The Pile)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0565. Min Range: -4.0565
Max Act: 3.8063. Min Act: -0.1700
Data Index: 4673703 (The Pile)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0565. Min Range: -4.0565
Max Act: 3.8063. Min Act: -0.1700
Data Index: 9022421 (The Pile)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0565. Min Range: -4.0565
Max Act: 3.8063. Min Act: -0.1700
Data Index: 285301 (The Pile)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0565. Min Range: -4.0565
Max Act: 3.7907. Min Act: -0.1700
Data Index: 1240454 (The Pile)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0565. Min Range: -4.0565
Max Act: 3.7907. Min Act: -0.1700
Data Index: 3564514 (The Pile)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0565. Min Range: -4.0565
Max Act: 3.7907. Min Act: -0.1700
Data Index: 617225 (The Pile)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19