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

Dataset: The Pile

Neuron 4140 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.5773. Min Act: -0.0000

Data Index: 1537869 (The Pile)

Max Activating Token Index: 557

Text #1

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.4132. Min Act: -0.0000

Data Index: 397566 (The Pile)

Max Activating Token Index: 1013

Text #2

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.3371. Min Act: -0.0000

Data Index: 157709 (The Pile)

Max Activating Token Index: 81

Text #3

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.3433. Min Act: -0.0000

Data Index: 1457687 (The Pile)

Max Activating Token Index: 456

Text #4

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.3764. Min Act: -0.0000

Data Index: 830549 (The Pile)

Max Activating Token Index: 852

Text #5

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.2846. Min Act: -0.0000

Data Index: 864119 (The Pile)

Max Activating Token Index: 401

Text #6

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.2586. Min Act: -0.0000

Data Index: 424297 (The Pile)

Max Activating Token Index: 239

Text #7

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.2511. Min Act: -0.0000

Data Index: 1236062 (The Pile)

Max Activating Token Index: 911

Text #8

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.2826. Min Act: -0.0000

Data Index: 1839700 (The Pile)

Max Activating Token Index: 463

Text #9

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.2739. Min Act: -0.0000

Data Index: 1888794 (The Pile)

Max Activating Token Index: 231

Text #10

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.2537. Min Act: -0.0000

Data Index: 1771329 (The Pile)

Max Activating Token Index: 663

Text #11

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.2495. Min Act: -0.0000

Data Index: 661508 (The Pile)

Max Activating Token Index: 287

Text #12

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.2376. Min Act: -0.0000

Data Index: 1343551 (The Pile)

Max Activating Token Index: 332

Text #13

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.2511. Min Act: -0.0000

Data Index: 1224582 (The Pile)

Max Activating Token Index: 221

Text #14

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.2224. Min Act: -0.0000

Data Index: 459301 (The Pile)

Max Activating Token Index: 1020

Text #15

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.2312. Min Act: -0.0000

Data Index: 1712871 (The Pile)

Max Activating Token Index: 906

Text #16

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.2152. Min Act: -0.0000

Data Index: 1655406 (The Pile)

Max Activating Token Index: 631

Text #17

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.2464. Min Act: -0.0000

Data Index: 985433 (The Pile)

Max Activating Token Index: 69

Text #18

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.2338. Min Act: -0.0000

Data Index: 1364517 (The Pile)

Max Activating Token Index: 248

Text #19

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.2370. Min Act: -0.0000

Data Index: 649819 (The Pile)

Max Activating Token Index: 901