Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3326 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4866. Min Act: -0.0000

Data Index: 742729 (The Pile)

Max Activating Token Index: 263

Text #1

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.3936. Min Act: -0.0000

Data Index: 1726299 (The Pile)

Max Activating Token Index: 675

Text #2

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.3394. Min Act: -0.0000

Data Index: 1167271 (The Pile)

Max Activating Token Index: 463

Text #3

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.3516. Min Act: -0.0000

Data Index: 1378589 (The Pile)

Max Activating Token Index: 999

Text #4

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.3009. Min Act: -0.0000

Data Index: 608697 (The Pile)

Max Activating Token Index: 538

Text #5

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.2874. Min Act: -0.0000

Data Index: 840625 (The Pile)

Max Activating Token Index: 127

Text #6

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.2741. Min Act: -0.0000

Data Index: 1285042 (The Pile)

Max Activating Token Index: 353

Text #7

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.2872. Min Act: -0.0000

Data Index: 788541 (The Pile)

Max Activating Token Index: 821

Text #8

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.2569. Min Act: -0.0000

Data Index: 736316 (The Pile)

Max Activating Token Index: 510

Text #9

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.2553. Min Act: -0.0000

Data Index: 486578 (The Pile)

Max Activating Token Index: 110

Text #10

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.2630. Min Act: -0.0000

Data Index: 78384 (The Pile)

Max Activating Token Index: 64

Text #11

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.2518. Min Act: -0.0000

Data Index: 84770 (The Pile)

Max Activating Token Index: 737

Text #12

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.2651. Min Act: -0.0000

Data Index: 1306977 (The Pile)

Max Activating Token Index: 946

Text #13

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.2434. Min Act: -0.0000

Data Index: 1741210 (The Pile)

Max Activating Token Index: 259

Text #14

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.2435. Min Act: -0.0000

Data Index: 1096530 (The Pile)

Max Activating Token Index: 517

Text #15

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.2192. Min Act: -0.0000

Data Index: 195752 (The Pile)

Max Activating Token Index: 945

Text #16

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.2361. Min Act: -0.0000

Data Index: 723650 (The Pile)

Max Activating Token Index: 130

Text #17

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.2351. Min Act: -0.0000

Data Index: 774734 (The Pile)

Max Activating Token Index: 654

Text #18

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.2326. Min Act: -0.0000

Data Index: 406460 (The Pile)

Max Activating Token Index: 192

Text #19

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.2158. Min Act: -0.0000

Data Index: 414268 (The Pile)

Max Activating Token Index: 632