Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3054 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.3729. Min Act: -0.0000

Data Index: 785071 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.3168. Min Act: -0.0000

Data Index: 1236306 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.3102. Min Act: -0.0000

Data Index: 689755 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2911. Min Act: -0.0000

Data Index: 387992 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2778. Min Act: -0.0000

Data Index: 729974 (C4 (Web Text))

Max Activating Token Index: 706

Text #5

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2736. Min Act: -0.0000

Data Index: 1107441 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2642. Min Act: -0.0000

Data Index: 801489 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2524. Min Act: -0.0000

Data Index: 270513 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2620. Min Act: -0.0000

Data Index: 1001351 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2366. Min Act: -0.0000

Data Index: 240884 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2413. Min Act: -0.0000

Data Index: 510160 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2330. Min Act: -0.0000

Data Index: 1291519 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2245. Min Act: -0.0000

Data Index: 611751 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2321. Min Act: -0.0000

Data Index: 933272 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2369. Min Act: -0.0000

Data Index: 661646 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2190. Min Act: -0.0000

Data Index: 1005271 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2322. Min Act: -0.0000

Data Index: 609782 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2293. Min Act: -0.0000

Data Index: 684671 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2262. Min Act: -0.0000

Data Index: 706383 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2251. Min Act: -0.0000

Data Index: 539368 (C4 (Web Text))

Max Activating Token Index: 994