Model: None
Dataset: The Pile
Neuron 2819 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.8077. Min Range: -3.8077
Max Act: 3.8077. Min Act: -0.1700
Data Index: 6756481 (The Pile)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8077. Min Range: -3.8077
Max Act: 3.7764. Min Act: -0.1700
Data Index: 4724759 (The Pile)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8077. Min Range: -3.8077
Max Act: 3.7451. Min Act: -0.1700
Data Index: 4684028 (The Pile)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8077. Min Range: -3.8077
Max Act: 3.7138. Min Act: -0.1700
Data Index: 8686020 (The Pile)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8077. Min Range: -3.8077
Max Act: 3.7138. Min Act: -0.1700
Data Index: 5483542 (The Pile)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8077. Min Range: -3.8077
Max Act: 3.6825. Min Act: -0.1700
Data Index: 4714454 (The Pile)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8077. Min Range: -3.8077
Max Act: 3.6825. Min Act: -0.1700
Data Index: 3402837 (The Pile)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8077. Min Range: -3.8077
Max Act: 3.6825. Min Act: -0.1700
Data Index: 1804896 (The Pile)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8077. Min Range: -3.8077
Max Act: 3.6669. Min Act: -0.1700
Data Index: 2685214 (The Pile)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8077. Min Range: -3.8077
Max Act: 3.6669. Min Act: -0.1700
Data Index: 2422218 (The Pile)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8077. Min Range: -3.8077
Max Act: 3.6669. Min Act: -0.1700
Data Index: 2159829 (The Pile)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8077. Min Range: -3.8077
Max Act: 3.6669. Min Act: -0.1700
Data Index: 6196055 (The Pile)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8077. Min Range: -3.8077
Max Act: 3.6512. Min Act: -0.1700
Data Index: 2123390 (The Pile)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8077. Min Range: -3.8077
Max Act: 3.6356. Min Act: -0.1700
Data Index: 10758026 (The Pile)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8077. Min Range: -3.8077
Max Act: 3.6199. Min Act: -0.1700
Data Index: 10377529 (The Pile)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8077. Min Range: -3.8077
Max Act: 3.6199. Min Act: -0.1700
Data Index: 7761081 (The Pile)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8077. Min Range: -3.8077
Max Act: 3.6199. Min Act: -0.1700
Data Index: 2949288 (The Pile)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8077. Min Range: -3.8077
Max Act: 3.6199. Min Act: -0.1700
Data Index: 9627586 (The Pile)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8077. Min Range: -3.8077
Max Act: 3.6199. Min Act: -0.1700
Data Index: 2639476 (The Pile)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8077. Min Range: -3.8077
Max Act: 3.6043. Min Act: -0.1700
Data Index: 4090608 (The Pile)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19