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

Dataset: The Pile

Neuron 3560 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1487. Min Range: -2.1487

Max Act: 2.1487. Min Act: -0.0000

Data Index: 1679356 (The Pile)

Max Activating Token Index: 498

Text #1

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.6611. Min Act: -0.0000

Data Index: 1498552 (The Pile)

Max Activating Token Index: 571

Text #2

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.5538. Min Act: -0.0000

Data Index: 1943624 (The Pile)

Max Activating Token Index: 1014

Text #3

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.6143. Min Act: -0.0000

Data Index: 818343 (The Pile)

Max Activating Token Index: 876

Text #4

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.4783. Min Act: -0.0000

Data Index: 952767 (The Pile)

Max Activating Token Index: 765

Text #5

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.5604. Min Act: -0.0000

Data Index: 1203157 (The Pile)

Max Activating Token Index: 662

Text #6

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.5890. Min Act: -0.0000

Data Index: 1879510 (The Pile)

Max Activating Token Index: 992

Text #7

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.4095. Min Act: -0.0000

Data Index: 1708662 (The Pile)

Max Activating Token Index: 289

Text #8

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.3774. Min Act: -0.0000

Data Index: 262999 (The Pile)

Max Activating Token Index: 988

Text #9

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.4581. Min Act: -0.0000

Data Index: 358986 (The Pile)

Max Activating Token Index: 941

Text #10

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.3955. Min Act: -0.0000

Data Index: 922300 (The Pile)

Max Activating Token Index: 546

Text #11

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.3292. Min Act: -0.0000

Data Index: 71043 (The Pile)

Max Activating Token Index: 558

Text #12

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.2809. Min Act: -0.0000

Data Index: 1503819 (The Pile)

Max Activating Token Index: 417

Text #13

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.4120. Min Act: -0.0000

Data Index: 1091278 (The Pile)

Max Activating Token Index: 541

Text #14

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.4472. Min Act: -0.0000

Data Index: 994643 (The Pile)

Max Activating Token Index: 569

Text #15

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.3523. Min Act: -0.0000

Data Index: 1051625 (The Pile)

Max Activating Token Index: 931

Text #16

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.4083. Min Act: -0.0000

Data Index: 1962186 (The Pile)

Max Activating Token Index: 934

Text #17

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.2702. Min Act: -0.0000

Data Index: 791045 (The Pile)

Max Activating Token Index: 737

Text #18

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.2365. Min Act: -0.0000

Data Index: 1376563 (The Pile)

Max Activating Token Index: 860

Text #19

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.4975. Min Act: -0.0000

Data Index: 1320067 (The Pile)

Max Activating Token Index: 981