Model: None
Dataset: The Pile
Neuron 3488 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.8016. Min Range: -3.8016
Max Act: 3.8016. Min Act: -0.1700
Data Index: 5666636 (The Pile)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8016. Min Range: -3.8016
Max Act: 3.8016. Min Act: -0.1700
Data Index: 304907 (The Pile)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8016. Min Range: -3.8016
Max Act: 3.8016. Min Act: -0.1700
Data Index: 9761481 (The Pile)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8016. Min Range: -3.8016
Max Act: 3.7390. Min Act: -0.1700
Data Index: 740374 (The Pile)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8016. Min Range: -3.8016
Max Act: 3.7234. Min Act: -0.1700
Data Index: 281379 (The Pile)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8016. Min Range: -3.8016
Max Act: 3.7234. Min Act: -0.1700
Data Index: 6774024 (The Pile)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8016. Min Range: -3.8016
Max Act: 3.6921. Min Act: -0.1700
Data Index: 6001224 (The Pile)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8016. Min Range: -3.8016
Max Act: 3.6921. Min Act: -0.1700
Data Index: 3928098 (The Pile)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8016. Min Range: -3.8016
Max Act: 3.6921. Min Act: -0.1700
Data Index: 1651700 (The Pile)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8016. Min Range: -3.8016
Max Act: 3.6764. Min Act: -0.1700
Data Index: 8124460 (The Pile)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8016. Min Range: -3.8016
Max Act: 3.6608. Min Act: -0.1700
Data Index: 10753338 (The Pile)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8016. Min Range: -3.8016
Max Act: 3.6608. Min Act: -0.1700
Data Index: 637949 (The Pile)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8016. Min Range: -3.8016
Max Act: 3.6451. Min Act: -0.1700
Data Index: 4626389 (The Pile)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8016. Min Range: -3.8016
Max Act: 3.6451. Min Act: -0.1700
Data Index: 10091100 (The Pile)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8016. Min Range: -3.8016
Max Act: 3.6451. Min Act: -0.1700
Data Index: 8937212 (The Pile)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8016. Min Range: -3.8016
Max Act: 3.6451. Min Act: -0.1700
Data Index: 2181111 (The Pile)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8016. Min Range: -3.8016
Max Act: 3.6451. Min Act: -0.1700
Data Index: 5466978 (The Pile)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8016. Min Range: -3.8016
Max Act: 3.6451. Min Act: -0.1700
Data Index: 8720230 (The Pile)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8016. Min Range: -3.8016
Max Act: 3.6295. Min Act: -0.1700
Data Index: 101303 (The Pile)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8016. Min Range: -3.8016
Max Act: 3.6295. Min Act: -0.1700
Data Index: 8678582 (The Pile)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19