Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 4042 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.7634. Min Range: -0.7634
Max Act: 0.7170. Min Act: -0.0001
Data Index: 1494832 (The Pile)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7634. Min Range: -0.7634
Max Act: 0.7403. Min Act: -0.0001
Data Index: 400625 (The Pile)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7634. Min Range: -0.7634
Max Act: 0.6999. Min Act: -0.0001
Data Index: 99144 (The Pile)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7634. Min Range: -0.7634
Max Act: 0.7634. Min Act: -0.0001
Data Index: 1443861 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7634. Min Range: -0.7634
Max Act: 0.7253. Min Act: -0.0001
Data Index: 1701533 (The Pile)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7634. Min Range: -0.7634
Max Act: 0.7406. Min Act: -0.0001
Data Index: 362910 (The Pile)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7634. Min Range: -0.7634
Max Act: 0.6484. Min Act: -0.0001
Data Index: 1271892 (The Pile)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7634. Min Range: -0.7634
Max Act: 0.7033. Min Act: -0.0001
Data Index: 565215 (The Pile)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7634. Min Range: -0.7634
Max Act: 0.7360. Min Act: -0.0001
Data Index: 575337 (The Pile)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7634. Min Range: -0.7634
Max Act: 0.7425. Min Act: -0.0001
Data Index: 1840191 (The Pile)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7634. Min Range: -0.7634
Max Act: 0.6934. Min Act: -0.0001
Data Index: 591102 (The Pile)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7634. Min Range: -0.7634
Max Act: 0.6667. Min Act: -0.0001
Data Index: 1943620 (The Pile)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7634. Min Range: -0.7634
Max Act: 0.6341. Min Act: -0.0001
Data Index: 1731051 (The Pile)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7634. Min Range: -0.7634
Max Act: 0.6248. Min Act: -0.0001
Data Index: 466170 (The Pile)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7634. Min Range: -0.7634
Max Act: 0.6905. Min Act: -0.0001
Data Index: 1981741 (The Pile)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7634. Min Range: -0.7634
Max Act: 0.7138. Min Act: -0.0001
Data Index: 1724834 (The Pile)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7634. Min Range: -0.7634
Max Act: 0.6328. Min Act: -0.0001
Data Index: 1849574 (The Pile)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7634. Min Range: -0.7634
Max Act: 0.6346. Min Act: -0.0001
Data Index: 839897 (The Pile)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7634. Min Range: -0.7634
Max Act: 0.6504. Min Act: -0.0001
Data Index: 46922 (The Pile)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7634. Min Range: -0.7634
Max Act: 0.6433. Min Act: -0.0001
Data Index: 514259 (The Pile)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19