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

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

Neuron 516 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6577. Min Range: -3.6577

Max Act: 3.6577. Min Act: -0.0000

Data Index: 54354 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 3.6577. Min Range: -3.6577

Max Act: 3.2363. Min Act: -0.0000

Data Index: 28941 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 3.6577. Min Range: -3.6577

Max Act: 2.8564. Min Act: -0.0000

Data Index: 1237268 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 3.6577. Min Range: -3.6577

Max Act: 2.9473. Min Act: -0.0000

Data Index: 61371 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 3.6577. Min Range: -3.6577

Max Act: 2.6548. Min Act: -0.0000

Data Index: 236162 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 3.6577. Min Range: -3.6577

Max Act: 2.8331. Min Act: -0.0000

Data Index: 540600 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 3.6577. Min Range: -3.6577

Max Act: 2.5894. Min Act: -0.0000

Data Index: 1116189 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 3.6577. Min Range: -3.6577

Max Act: 2.6742. Min Act: -0.0000

Data Index: 1279450 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 3.6577. Min Range: -3.6577

Max Act: 2.5447. Min Act: -0.0000

Data Index: 403809 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 3.6577. Min Range: -3.6577

Max Act: 2.8018. Min Act: -0.0000

Data Index: 729716 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 3.6577. Min Range: -3.6577

Max Act: 2.3430. Min Act: -0.0000

Data Index: 224230 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 3.6577. Min Range: -3.6577

Max Act: 2.8223. Min Act: -0.0000

Data Index: 685688 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 3.6577. Min Range: -3.6577

Max Act: 2.4491. Min Act: -0.0000

Data Index: 1022911 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 3.6577. Min Range: -3.6577

Max Act: 2.5403. Min Act: -0.0000

Data Index: 1040146 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 3.6577. Min Range: -3.6577

Max Act: 2.4489. Min Act: -0.0000

Data Index: 1311099 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 3.6577. Min Range: -3.6577

Max Act: 2.4495. Min Act: -0.0000

Data Index: 1221978 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 3.6577. Min Range: -3.6577

Max Act: 2.2957. Min Act: -0.0000

Data Index: 537207 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 3.6577. Min Range: -3.6577

Max Act: 2.4491. Min Act: -0.0000

Data Index: 876485 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 3.6577. Min Range: -3.6577

Max Act: 2.4240. Min Act: -0.0000

Data Index: 965389 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 3.6577. Min Range: -3.6577

Max Act: 2.2812. Min Act: -0.0000

Data Index: 323283 (C4 (Web Text))

Max Activating Token Index: 752