Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 1446 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 1.1605. Min Range: -1.1605
Max Act: 1.1605. Min Act: -0.0001
Data Index: 815323 (The Pile)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1605. Min Range: -1.1605
Max Act: 1.0710. Min Act: -0.0001
Data Index: 1465139 (The Pile)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1605. Min Range: -1.1605
Max Act: 1.0815. Min Act: -0.0001
Data Index: 687660 (The Pile)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1605. Min Range: -1.1605
Max Act: 1.0320. Min Act: -0.0001
Data Index: 1354692 (The Pile)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1605. Min Range: -1.1605
Max Act: 0.9803. Min Act: -0.0001
Data Index: 249705 (The Pile)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1605. Min Range: -1.1605
Max Act: 0.9020. Min Act: -0.0001
Data Index: 560568 (The Pile)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1605. Min Range: -1.1605
Max Act: 0.9502. Min Act: -0.0001
Data Index: 1856773 (The Pile)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1605. Min Range: -1.1605
Max Act: 0.9762. Min Act: -0.0001
Data Index: 549855 (The Pile)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1605. Min Range: -1.1605
Max Act: 1.0248. Min Act: -0.0001
Data Index: 961444 (The Pile)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1605. Min Range: -1.1605
Max Act: 0.9278. Min Act: -0.0001
Data Index: 831357 (The Pile)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1605. Min Range: -1.1605
Max Act: 0.9215. Min Act: -0.0001
Data Index: 686183 (The Pile)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1605. Min Range: -1.1605
Max Act: 0.9215. Min Act: -0.0001
Data Index: 267222 (The Pile)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1605. Min Range: -1.1605
Max Act: 0.9262. Min Act: -0.0001
Data Index: 268717 (The Pile)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1605. Min Range: -1.1605
Max Act: 0.8691. Min Act: -0.0001
Data Index: 426676 (The Pile)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1605. Min Range: -1.1605
Max Act: 0.8660. Min Act: -0.0001
Data Index: 28217 (The Pile)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1605. Min Range: -1.1605
Max Act: 0.7844. Min Act: -0.0001
Data Index: 809525 (The Pile)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1605. Min Range: -1.1605
Max Act: 0.8501. Min Act: -0.0001
Data Index: 964657 (The Pile)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1605. Min Range: -1.1605
Max Act: 0.8339. Min Act: -0.0001
Data Index: 158479 (The Pile)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1605. Min Range: -1.1605
Max Act: 0.8481. Min Act: -0.0001
Data Index: 23150 (The Pile)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1605. Min Range: -1.1605
Max Act: 0.8635. Min Act: -0.0001
Data Index: 192834 (The Pile)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19