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

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

Neuron 3588 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.4487. Min Act: -0.0000

Data Index: 1121810 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.3713. Min Act: -0.0000

Data Index: 1033998 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.2974. Min Act: -0.0001

Data Index: 375428 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.3255. Min Act: -0.0000

Data Index: 713110 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.3075. Min Act: -0.0000

Data Index: 71509 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.3027. Min Act: -0.0000

Data Index: 623336 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.3002. Min Act: -0.0001

Data Index: 589204 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.2770. Min Act: -0.0001

Data Index: 619634 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.2968. Min Act: -0.0000

Data Index: 387941 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.2902. Min Act: -0.0000

Data Index: 180862 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.2782. Min Act: -0.0000

Data Index: 908351 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.2607. Min Act: -0.0000

Data Index: 531602 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.2776. Min Act: -0.0000

Data Index: 776585 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.2709. Min Act: -0.0000

Data Index: 1074055 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.2579. Min Act: -0.0000

Data Index: 1113099 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.2619. Min Act: -0.0000

Data Index: 841653 (C4 (Web Text))

Max Activating Token Index: 468

Text #16

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.2530. Min Act: -0.0000

Data Index: 267428 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.2522. Min Act: -0.0000

Data Index: 1324169 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.2588. Min Act: -0.0000

Data Index: 701092 (C4 (Web Text))

Max Activating Token Index: 801

Text #19

Max Range: 0.4487. Min Range: -0.4487

Max Act: 0.2398. Min Act: -0.0000

Data Index: 1136445 (C4 (Web Text))

Max Activating Token Index: 558