Model: None
Dataset: The Pile
Neuron 642 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')
Text #0
Max Range: 3.0009. Min Range: -3.0009
Max Act: 3.0009. Min Act: -0.1700
Data Index: 2147932 (The Pile)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0009. Min Range: -3.0009
Max Act: 2.9851. Min Act: -0.1700
Data Index: 3539677 (The Pile)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0009. Min Range: -3.0009
Max Act: 2.9376. Min Act: -0.1700
Data Index: 1438045 (The Pile)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0009. Min Range: -3.0009
Max Act: 2.8742. Min Act: -0.1700
Data Index: 434461 (The Pile)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0009. Min Range: -3.0009
Max Act: 2.8583. Min Act: -0.1700
Data Index: 6574507 (The Pile)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0009. Min Range: -3.0009
Max Act: 2.8583. Min Act: -0.1700
Data Index: 3172207 (The Pile)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0009. Min Range: -3.0009
Max Act: 2.8583. Min Act: -0.1700
Data Index: 5989493 (The Pile)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0009. Min Range: -3.0009
Max Act: 2.8424. Min Act: -0.1700
Data Index: 5384262 (The Pile)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0009. Min Range: -3.0009
Max Act: 2.8265. Min Act: -0.1700
Data Index: 10085502 (The Pile)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0009. Min Range: -3.0009
Max Act: 2.8106. Min Act: -0.1700
Data Index: 4656176 (The Pile)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0009. Min Range: -3.0009
Max Act: 2.8106. Min Act: -0.1700
Data Index: 10702064 (The Pile)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0009. Min Range: -3.0009
Max Act: 2.7947. Min Act: -0.1700
Data Index: 353630 (The Pile)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0009. Min Range: -3.0009
Max Act: 2.7947. Min Act: -0.1700
Data Index: 20173 (The Pile)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0009. Min Range: -3.0009
Max Act: 2.7947. Min Act: -0.1700
Data Index: 4156920 (The Pile)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0009. Min Range: -3.0009
Max Act: 2.7947. Min Act: -0.1700
Data Index: 8636202 (The Pile)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0009. Min Range: -3.0009
Max Act: 2.7947. Min Act: -0.1700
Data Index: 7355203 (The Pile)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0009. Min Range: -3.0009
Max Act: 2.7787. Min Act: -0.1700
Data Index: 9566739 (The Pile)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0009. Min Range: -3.0009
Max Act: 2.7787. Min Act: -0.1700
Data Index: 5329319 (The Pile)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0009. Min Range: -3.0009
Max Act: 2.7628. Min Act: -0.1700
Data Index: 6545824 (The Pile)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0009. Min Range: -3.0009
Max Act: 2.7468. Min Act: -0.1700
Data Index: 6791572 (The Pile)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19