Model: None
Dataset: The Pile
Neuron 3791 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.7582. Min Act: -0.1700
Data Index: 1131419 (The Pile)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.7269. Min Act: -0.1700
Data Index: 1940514 (The Pile)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.7113. Min Act: -0.1700
Data Index: 4494839 (The Pile)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.6487. Min Act: -0.1700
Data Index: 1305769 (The Pile)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.5547. Min Act: -0.1700
Data Index: 9700429 (The Pile)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.5391. Min Act: -0.1700
Data Index: 4700062 (The Pile)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.5234. Min Act: -0.1700
Data Index: 4458904 (The Pile)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.5078. Min Act: -0.1700
Data Index: 10189046 (The Pile)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.4764. Min Act: -0.1700
Data Index: 2719302 (The Pile)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.4607. Min Act: -0.1700
Data Index: 6120756 (The Pile)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.4607. Min Act: -0.1700
Data Index: 10634058 (The Pile)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.4607. Min Act: -0.1700
Data Index: 3735296 (The Pile)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.4607. Min Act: -0.1700
Data Index: 2658045 (The Pile)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.4607. Min Act: -0.1700
Data Index: 3830183 (The Pile)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.4607. Min Act: -0.1700
Data Index: 1627051 (The Pile)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.4451. Min Act: -0.1700
Data Index: 9045936 (The Pile)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.4451. Min Act: -0.1700
Data Index: 4903165 (The Pile)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.4451. Min Act: -0.1700
Data Index: 3579582 (The Pile)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.4451. Min Act: -0.1700
Data Index: 2189116 (The Pile)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.4451. Min Act: -0.1700
Data Index: 2256856 (The Pile)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19