Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3367 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.3468. Min Act: -0.0000

Data Index: 503646 (The Pile)

Max Activating Token Index: 456

Text #1

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.5459. Min Act: -0.0000

Data Index: 1886151 (The Pile)

Max Activating Token Index: 380

Text #2

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.4015. Min Act: -0.0000

Data Index: 351834 (The Pile)

Max Activating Token Index: 358

Text #3

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.4327. Min Act: -0.0000

Data Index: 1832171 (The Pile)

Max Activating Token Index: 428

Text #4

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.3290. Min Act: -0.0000

Data Index: 693779 (The Pile)

Max Activating Token Index: 480

Text #5

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.3972. Min Act: -0.0000

Data Index: 1479188 (The Pile)

Max Activating Token Index: 199

Text #6

Max Range: 1.5459. Min Range: -1.5459

Max Act: 0.9632. Min Act: -0.0000

Data Index: 139347 (The Pile)

Max Activating Token Index: 866

Text #7

Max Range: 1.5459. Min Range: -1.5459

Max Act: 0.9910. Min Act: -0.0000

Data Index: 609091 (The Pile)

Max Activating Token Index: 237

Text #8

Max Range: 1.5459. Min Range: -1.5459

Max Act: 0.9274. Min Act: -0.0001

Data Index: 71192 (The Pile)

Max Activating Token Index: 915

Text #9

Max Range: 1.5459. Min Range: -1.5459

Max Act: 0.9987. Min Act: -0.0000

Data Index: 1915516 (The Pile)

Max Activating Token Index: 812

Text #10

Max Range: 1.5459. Min Range: -1.5459

Max Act: 0.9743. Min Act: -0.0001

Data Index: 1006837 (The Pile)

Max Activating Token Index: 589

Text #11

Max Range: 1.5459. Min Range: -1.5459

Max Act: 0.9797. Min Act: -0.0000

Data Index: 118680 (The Pile)

Max Activating Token Index: 1014

Text #12

Max Range: 1.5459. Min Range: -1.5459

Max Act: 0.7630. Min Act: -0.0000

Data Index: 690259 (The Pile)

Max Activating Token Index: 641

Text #13

Max Range: 1.5459. Min Range: -1.5459

Max Act: 0.8815. Min Act: -0.0000

Data Index: 1926159 (The Pile)

Max Activating Token Index: 66

Text #14

Max Range: 1.5459. Min Range: -1.5459

Max Act: 0.7327. Min Act: -0.0000

Data Index: 1461026 (The Pile)

Max Activating Token Index: 754

Text #15

Max Range: 1.5459. Min Range: -1.5459

Max Act: 0.8540. Min Act: -0.0000

Data Index: 1792568 (The Pile)

Max Activating Token Index: 887

Text #16

Max Range: 1.5459. Min Range: -1.5459

Max Act: 0.9440. Min Act: -0.0001

Data Index: 1835883 (The Pile)

Max Activating Token Index: 667

Text #17

Max Range: 1.5459. Min Range: -1.5459

Max Act: 0.7696. Min Act: 0.0000

Data Index: 422761 (The Pile)

Max Activating Token Index: 353

Text #18

Max Range: 1.5459. Min Range: -1.5459

Max Act: 0.9433. Min Act: -0.0000

Data Index: 766620 (The Pile)

Max Activating Token Index: 606

Text #19

Max Range: 1.5459. Min Range: -1.5459

Max Act: 0.7425. Min Act: -0.0000

Data Index: 60465 (The Pile)

Max Activating Token Index: 58