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

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

Neuron 672 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: 0.3667. Min Range: -0.3667

Max Act: 0.3448. Min Act: -0.0001

Data Index: 1047849 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.3667. Min Act: -0.0000

Data Index: 486135 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.3524. Min Act: -0.0000

Data Index: 1225099 (C4 (Web Text))

Max Activating Token Index: 341

Text #3

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.3578. Min Act: -0.0000

Data Index: 78009 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.3368. Min Act: -0.0000

Data Index: 311708 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.3366. Min Act: -0.0000

Data Index: 828589 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.3389. Min Act: -0.0000

Data Index: 578718 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.3171. Min Act: -0.0001

Data Index: 439400 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.3560. Min Act: -0.0001

Data Index: 860182 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.3026. Min Act: -0.0001

Data Index: 48114 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.3303. Min Act: -0.0001

Data Index: 169989 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.3262. Min Act: -0.0000

Data Index: 1272663 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.3240. Min Act: -0.0000

Data Index: 807888 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.3233. Min Act: -0.0001

Data Index: 1223368 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.3129. Min Act: -0.0000

Data Index: 453265 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.3011. Min Act: -0.0000

Data Index: 247672 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.3103. Min Act: -0.0001

Data Index: 397234 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.3284. Min Act: -0.0000

Data Index: 1071073 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.3306. Min Act: -0.0001

Data Index: 1221103 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.3190. Min Act: -0.0000

Data Index: 1357916 (C4 (Web Text))

Max Activating Token Index: 117