Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1370 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.1341. Min Range: -0.1341
Max Act: 0.1341. Min Act: -0.0000
Data Index: 329170 (The Pile)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1341. Min Range: -0.1341
Max Act: 0.0943. Min Act: -0.0000
Data Index: 311622 (The Pile)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1341. Min Range: -0.1341
Max Act: 0.0790. Min Act: -0.0001
Data Index: 322603 (The Pile)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1341. Min Range: -0.1341
Max Act: 0.0736. Min Act: -0.0001
Data Index: 1687173 (The Pile)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1341. Min Range: -0.1341
Max Act: 0.0700. Min Act: -0.0001
Data Index: 714888 (The Pile)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1341. Min Range: -0.1341
Max Act: 0.0727. Min Act: -0.0001
Data Index: 1670118 (The Pile)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1341. Min Range: -0.1341
Max Act: 0.0749. Min Act: -0.0001
Data Index: 1943469 (The Pile)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1341. Min Range: -0.1341
Max Act: 0.0660. Min Act: -0.0001
Data Index: 472697 (The Pile)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1341. Min Range: -0.1341
Max Act: 0.0721. Min Act: -0.0001
Data Index: 1479162 (The Pile)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1341. Min Range: -0.1341
Max Act: 0.0736. Min Act: -0.0001
Data Index: 332642 (The Pile)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1341. Min Range: -0.1341
Max Act: 0.0741. Min Act: -0.0001
Data Index: 1462396 (The Pile)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1341. Min Range: -0.1341
Max Act: 0.0729. Min Act: -0.0001
Data Index: 245420 (The Pile)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1341. Min Range: -0.1341
Max Act: 0.0704. Min Act: -0.0001
Data Index: 1577825 (The Pile)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1341. Min Range: -0.1341
Max Act: 0.0726. Min Act: -0.0001
Data Index: 519208 (The Pile)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1341. Min Range: -0.1341
Max Act: 0.0674. Min Act: -0.0001
Data Index: 1938050 (The Pile)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1341. Min Range: -0.1341
Max Act: 0.0699. Min Act: -0.0001
Data Index: 99121 (The Pile)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1341. Min Range: -0.1341
Max Act: 0.0688. Min Act: -0.0001
Data Index: 523937 (The Pile)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1341. Min Range: -0.1341
Max Act: 0.0625. Min Act: -0.0001
Data Index: 1830914 (The Pile)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1341. Min Range: -0.1341
Max Act: 0.0581. Min Act: -0.0001
Data Index: 1812776 (The Pile)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1341. Min Range: -0.1341
Max Act: 0.0644. Min Act: -0.0001
Data Index: 309458 (The Pile)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19