Model: None
Dataset: The Pile
Neuron 2567 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')
Text #0
Max Range: 2.5451. Min Range: -2.5451
Max Act: 2.5451. Min Act: -0.1700
Data Index: 8665975 (The Pile)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5451. Min Range: -2.5451
Max Act: 2.4317. Min Act: -0.1700
Data Index: 70791 (The Pile)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5451. Min Range: -2.5451
Max Act: 2.3172. Min Act: -0.1700
Data Index: 2739156 (The Pile)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5451. Min Range: -2.5451
Max Act: 2.3172. Min Act: -0.1700
Data Index: 2395250 (The Pile)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5451. Min Range: -2.5451
Max Act: 2.3172. Min Act: -0.1700
Data Index: 6121661 (The Pile)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5451. Min Range: -2.5451
Max Act: 2.3008. Min Act: -0.1700
Data Index: 5763392 (The Pile)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5451. Min Range: -2.5451
Max Act: 2.3008. Min Act: -0.1700
Data Index: 5795871 (The Pile)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5451. Min Range: -2.5451
Max Act: 2.2844. Min Act: -0.1700
Data Index: 6918001 (The Pile)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5451. Min Range: -2.5451
Max Act: 2.2679. Min Act: -0.1700
Data Index: 4490263 (The Pile)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5451. Min Range: -2.5451
Max Act: 2.2679. Min Act: -0.1700
Data Index: 547434 (The Pile)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5451. Min Range: -2.5451
Max Act: 2.2679. Min Act: -0.1700
Data Index: 4710150 (The Pile)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5451. Min Range: -2.5451
Max Act: 2.2679. Min Act: -0.1700
Data Index: 10492350 (The Pile)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5451. Min Range: -2.5451
Max Act: 2.2679. Min Act: -0.1700
Data Index: 2091285 (The Pile)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5451. Min Range: -2.5451
Max Act: 2.2679. Min Act: -0.1700
Data Index: 10251153 (The Pile)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5451. Min Range: -2.5451
Max Act: 2.2679. Min Act: -0.1700
Data Index: 7741434 (The Pile)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5451. Min Range: -2.5451
Max Act: 2.2349. Min Act: -0.1700
Data Index: 5840021 (The Pile)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5451. Min Range: -2.5451
Max Act: 2.2349. Min Act: -0.1700
Data Index: 1573771 (The Pile)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5451. Min Range: -2.5451
Max Act: 2.2349. Min Act: -0.1700
Data Index: 6231980 (The Pile)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5451. Min Range: -2.5451
Max Act: 2.2349. Min Act: -0.1700
Data Index: 1377762 (The Pile)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5451. Min Range: -2.5451
Max Act: 2.2349. Min Act: -0.1700
Data Index: 514683 (The Pile)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19