Model: None
Dataset: The Pile
Neuron 2805 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.0523. Min Range: -3.0523
Max Act: 3.0523. Min Act: -0.1700
Data Index: 1059234 (The Pile)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0523. Min Range: -3.0523
Max Act: 2.9258. Min Act: -0.1700
Data Index: 5493408 (The Pile)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0523. Min Range: -3.0523
Max Act: 2.9258. Min Act: -0.1700
Data Index: 7328886 (The Pile)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0523. Min Range: -3.0523
Max Act: 2.9099. Min Act: -0.1700
Data Index: 5279371 (The Pile)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0523. Min Range: -3.0523
Max Act: 2.8305. Min Act: -0.1700
Data Index: 9656261 (The Pile)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0523. Min Range: -3.0523
Max Act: 2.7828. Min Act: -0.1700
Data Index: 7886015 (The Pile)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0523. Min Range: -3.0523
Max Act: 2.7668. Min Act: -0.1700
Data Index: 5747803 (The Pile)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0523. Min Range: -3.0523
Max Act: 2.7509. Min Act: -0.1700
Data Index: 5105225 (The Pile)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0523. Min Range: -3.0523
Max Act: 2.7509. Min Act: -0.1700
Data Index: 1500183 (The Pile)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0523. Min Range: -3.0523
Max Act: 2.7509. Min Act: -0.1700
Data Index: 2592363 (The Pile)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0523. Min Range: -3.0523
Max Act: 2.7349. Min Act: -0.1700
Data Index: 7961803 (The Pile)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0523. Min Range: -3.0523
Max Act: 2.7189. Min Act: -0.1700
Data Index: 2677706 (The Pile)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0523. Min Range: -3.0523
Max Act: 2.7189. Min Act: -0.1700
Data Index: 6359623 (The Pile)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0523. Min Range: -3.0523
Max Act: 2.7189. Min Act: -0.1700
Data Index: 6136360 (The Pile)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0523. Min Range: -3.0523
Max Act: 2.7189. Min Act: -0.1700
Data Index: 4861982 (The Pile)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0523. Min Range: -3.0523
Max Act: 2.7189. Min Act: -0.1700
Data Index: 8793195 (The Pile)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0523. Min Range: -3.0523
Max Act: 2.7029. Min Act: -0.1700
Data Index: 1903252 (The Pile)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0523. Min Range: -3.0523
Max Act: 2.7029. Min Act: -0.1700
Data Index: 4823859 (The Pile)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0523. Min Range: -3.0523
Max Act: 2.7029. Min Act: -0.1700
Data Index: 1766108 (The Pile)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0523. Min Range: -3.0523
Max Act: 2.7029. Min Act: -0.1700
Data Index: 4562144 (The Pile)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19