Model: None
Dataset: The Pile
Neuron 3584 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.4605. Min Act: -0.1700
Data Index: 3545660 (The Pile)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.4605. Min Act: -0.1700
Data Index: 4035888 (The Pile)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.4292. Min Act: -0.1700
Data Index: 4620844 (The Pile)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.3821. Min Act: -0.1700
Data Index: 4547237 (The Pile)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.3821. Min Act: -0.1700
Data Index: 8225767 (The Pile)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.3821. Min Act: -0.1700
Data Index: 399333 (The Pile)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.3664. Min Act: -0.1700
Data Index: 9353614 (The Pile)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.3664. Min Act: -0.1700
Data Index: 838203 (The Pile)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.3664. Min Act: -0.1700
Data Index: 9606028 (The Pile)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.3351. Min Act: -0.1700
Data Index: 7232662 (The Pile)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.3351. Min Act: -0.1700
Data Index: 5135514 (The Pile)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.3194. Min Act: -0.1700
Data Index: 10350863 (The Pile)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.3194. Min Act: -0.1700
Data Index: 6290843 (The Pile)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.3194. Min Act: -0.1700
Data Index: 7681882 (The Pile)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.3037. Min Act: -0.1700
Data Index: 1903027 (The Pile)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.2879. Min Act: -0.1700
Data Index: 5231186 (The Pile)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.2879. Min Act: -0.1700
Data Index: 7725554 (The Pile)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.2722. Min Act: -0.1700
Data Index: 7875690 (The Pile)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.2722. Min Act: -0.1700
Data Index: 7029382 (The Pile)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.2722. Min Act: -0.1700
Data Index: 9083940 (The Pile)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19