Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3036 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.0513. Min Range: -3.0513

Max Act: 3.0513. Min Act: -0.0000

Data Index: 1291026 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 3.0513. Min Range: -3.0513

Max Act: 2.8430. Min Act: -0.0000

Data Index: 838909 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 3.0513. Min Range: -3.0513

Max Act: 2.7542. Min Act: -0.0000

Data Index: 1267208 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 3.0513. Min Range: -3.0513

Max Act: 2.8840. Min Act: -0.0000

Data Index: 180585 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 3.0513. Min Range: -3.0513

Max Act: 2.6372. Min Act: -0.0000

Data Index: 216519 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 3.0513. Min Range: -3.0513

Max Act: 2.4815. Min Act: -0.0000

Data Index: 612647 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 3.0513. Min Range: -3.0513

Max Act: 2.4196. Min Act: -0.0000

Data Index: 488747 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 3.0513. Min Range: -3.0513

Max Act: 2.3406. Min Act: -0.0000

Data Index: 1298956 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 3.0513. Min Range: -3.0513

Max Act: 2.1512. Min Act: -0.0000

Data Index: 839194 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 3.0513. Min Range: -3.0513

Max Act: 2.2383. Min Act: -0.0000

Data Index: 1165284 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 3.0513. Min Range: -3.0513

Max Act: 2.2329. Min Act: -0.0000

Data Index: 1099683 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 3.0513. Min Range: -3.0513

Max Act: 2.2035. Min Act: -0.0000

Data Index: 589225 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 3.0513. Min Range: -3.0513

Max Act: 2.3125. Min Act: -0.0000

Data Index: 1214880 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 3.0513. Min Range: -3.0513

Max Act: 2.1964. Min Act: -0.0000

Data Index: 876905 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 3.0513. Min Range: -3.0513

Max Act: 2.0576. Min Act: -0.0000

Data Index: 609929 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 3.0513. Min Range: -3.0513

Max Act: 2.2743. Min Act: -0.0000

Data Index: 1008465 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 3.0513. Min Range: -3.0513

Max Act: 2.1444. Min Act: -0.0000

Data Index: 727748 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 3.0513. Min Range: -3.0513

Max Act: 2.1529. Min Act: -0.0000

Data Index: 1046817 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 3.0513. Min Range: -3.0513

Max Act: 2.2426. Min Act: -0.0000

Data Index: 1344554 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 3.0513. Min Range: -3.0513

Max Act: 2.0826. Min Act: -0.0000

Data Index: 340283 (C4 (Web Text))

Max Activating Token Index: 670