Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2751 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.4782. Min Range: -2.4782
Max Act: 2.4782. Min Act: -0.0001
Data Index: 645623 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4782. Min Range: -2.4782
Max Act: 2.4469. Min Act: -0.0001
Data Index: 1359180 (C4 (Web Text))
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4782. Min Range: -2.4782
Max Act: 2.2741. Min Act: -0.0001
Data Index: 318479 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4782. Min Range: -2.4782
Max Act: 2.4330. Min Act: -0.0001
Data Index: 38033 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4782. Min Range: -2.4782
Max Act: 2.0410. Min Act: -0.0001
Data Index: 144977 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4782. Min Range: -2.4782
Max Act: 2.2012. Min Act: -0.0001
Data Index: 164642 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4782. Min Range: -2.4782
Max Act: 2.0516. Min Act: -0.0001
Data Index: 247478 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4782. Min Range: -2.4782
Max Act: 2.1649. Min Act: -0.0001
Data Index: 517714 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4782. Min Range: -2.4782
Max Act: 2.0494. Min Act: -0.0001
Data Index: 307611 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4782. Min Range: -2.4782
Max Act: 2.0542. Min Act: -0.0001
Data Index: 1003706 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4782. Min Range: -2.4782
Max Act: 2.1639. Min Act: -0.0001
Data Index: 370262 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4782. Min Range: -2.4782
Max Act: 1.9597. Min Act: -0.0001
Data Index: 1050371 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4782. Min Range: -2.4782
Max Act: 2.0686. Min Act: -0.0001
Data Index: 518364 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4782. Min Range: -2.4782
Max Act: 2.1632. Min Act: -0.0001
Data Index: 1156180 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4782. Min Range: -2.4782
Max Act: 1.8997. Min Act: -0.0001
Data Index: 11852 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4782. Min Range: -2.4782
Max Act: 2.0927. Min Act: -0.0001
Data Index: 1085591 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4782. Min Range: -2.4782
Max Act: 1.9275. Min Act: -0.0001
Data Index: 871527 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4782. Min Range: -2.4782
Max Act: 2.0792. Min Act: -0.0001
Data Index: 1244032 (C4 (Web Text))
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4782. Min Range: -2.4782
Max Act: 1.8564. Min Act: -0.0001
Data Index: 511441 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4782. Min Range: -2.4782
Max Act: 1.9481. Min Act: -0.0001
Data Index: 1030387 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19