Model: None
Dataset: The Pile
Neuron 495 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.3939. Min Range: -2.3939
Max Act: 2.3939. Min Act: -0.1700
Data Index: 9711246 (The Pile)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3939. Min Range: -2.3939
Max Act: 2.3939. Min Act: -0.1700
Data Index: 9000568 (The Pile)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3939. Min Range: -2.3939
Max Act: 2.3120. Min Act: -0.1700
Data Index: 2182130 (The Pile)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3939. Min Range: -2.3939
Max Act: 2.3284. Min Act: -0.1700
Data Index: 1521853 (The Pile)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3939. Min Range: -2.3939
Max Act: 2.3284. Min Act: -0.1700
Data Index: 4423497 (The Pile)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3939. Min Range: -2.3939
Max Act: 2.3120. Min Act: -0.1700
Data Index: 484549 (The Pile)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3939. Min Range: -2.3939
Max Act: 2.2461. Min Act: -0.1700
Data Index: 3439732 (The Pile)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3939. Min Range: -2.3939
Max Act: 2.2626. Min Act: -0.1700
Data Index: 3196833 (The Pile)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3939. Min Range: -2.3939
Max Act: 2.2956. Min Act: -0.1700
Data Index: 4116487 (The Pile)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3939. Min Range: -2.3939
Max Act: 2.2791. Min Act: -0.1700
Data Index: 2520125 (The Pile)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3939. Min Range: -2.3939
Max Act: 2.1965. Min Act: -0.1700
Data Index: 273913 (The Pile)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3939. Min Range: -2.3939
Max Act: 2.2626. Min Act: -0.1700
Data Index: 4156937 (The Pile)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3939. Min Range: -2.3939
Max Act: 2.2296. Min Act: -0.1700
Data Index: 585193 (The Pile)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3939. Min Range: -2.3939
Max Act: 2.1965. Min Act: -0.1700
Data Index: 1179607 (The Pile)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3939. Min Range: -2.3939
Max Act: 2.2296. Min Act: -0.1700
Data Index: 4469597 (The Pile)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3939. Min Range: -2.3939
Max Act: 2.2131. Min Act: -0.1700
Data Index: 5606523 (The Pile)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3939. Min Range: -2.3939
Max Act: 2.2131. Min Act: -0.1700
Data Index: 9577045 (The Pile)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3939. Min Range: -2.3939
Max Act: 2.2131. Min Act: -0.1700
Data Index: 8785168 (The Pile)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3939. Min Range: -2.3939
Max Act: 2.2296. Min Act: -0.1700
Data Index: 10292232 (The Pile)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3939. Min Range: -2.3939
Max Act: 2.2296. Min Act: -0.1700
Data Index: 547423 (The Pile)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19