Model: None
Dataset: The Pile
Neuron 472 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.8038. Min Act: -0.1700
Data Index: 5137222 (The Pile)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.7413. Min Act: -0.1699
Data Index: 6337189 (The Pile)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.4913. Min Act: -0.0517
Data Index: 6655036 (The Pile)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.4601. Min Act: -0.1700
Data Index: 5619120 (The Pile)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.3976. Min Act: -0.1700
Data Index: 2232499 (The Pile)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.3663. Min Act: -0.1700
Data Index: 2361838 (The Pile)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.3663. Min Act: -0.1700
Data Index: 8843739 (The Pile)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.3038. Min Act: -0.1700
Data Index: 10460822 (The Pile)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.3038. Min Act: -0.1699
Data Index: 680662 (The Pile)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.1163. Min Act: -0.1700
Data Index: 10147274 (The Pile)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.0850. Min Act: -0.1700
Data Index: 6477861 (The Pile)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.0850. Min Act: -0.1699
Data Index: 9731617 (The Pile)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.0537. Min Act: -0.1700
Data Index: 1333612 (The Pile)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.0225. Min Act: -0.1699
Data Index: 9925975 (The Pile)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.0537. Min Act: -0.1700
Data Index: 3551426 (The Pile)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.0537. Min Act: -0.1699
Data Index: 6435314 (The Pile)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.0225. Min Act: -0.1699
Data Index: 3604287 (The Pile)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8038. Min Range: -4.8038
Max Act: 3.9912. Min Act: -0.1699
Data Index: 4349033 (The Pile)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8038. Min Range: -4.8038
Max Act: 3.9756. Min Act: -0.1700
Data Index: 7169492 (The Pile)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8038. Min Range: -4.8038
Max Act: 3.9287. Min Act: -0.1699
Data Index: 1207695 (The Pile)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19