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

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

Neuron 5659 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4480. Min Range: -1.4480

Max Act: 1.4480. Min Act: -0.0000

Data Index: 506615 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 1.4480. Min Range: -1.4480

Max Act: 1.1689. Min Act: -0.0000

Data Index: 295316 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 1.4480. Min Range: -1.4480

Max Act: 1.1521. Min Act: -0.0000

Data Index: 372699 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 1.4480. Min Range: -1.4480

Max Act: 1.2012. Min Act: -0.0000

Data Index: 272843 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 1.4480. Min Range: -1.4480

Max Act: 1.1250. Min Act: -0.0000

Data Index: 1140243 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 1.4480. Min Range: -1.4480

Max Act: 1.0533. Min Act: -0.0000

Data Index: 789056 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 1.4480. Min Range: -1.4480

Max Act: 1.1893. Min Act: -0.0000

Data Index: 860131 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 1.4480. Min Range: -1.4480

Max Act: 1.1534. Min Act: -0.0000

Data Index: 1353462 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 1.4480. Min Range: -1.4480

Max Act: 1.0785. Min Act: -0.0000

Data Index: 745613 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 1.4480. Min Range: -1.4480

Max Act: 1.0131. Min Act: -0.0000

Data Index: 586405 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 1.4480. Min Range: -1.4480

Max Act: 1.0914. Min Act: -0.0000

Data Index: 67790 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 1.4480. Min Range: -1.4480

Max Act: 1.1310. Min Act: -0.0000

Data Index: 119820 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 1.4480. Min Range: -1.4480

Max Act: 0.9114. Min Act: -0.0000

Data Index: 718995 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 1.4480. Min Range: -1.4480

Max Act: 0.8981. Min Act: -0.0000

Data Index: 942161 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 1.4480. Min Range: -1.4480

Max Act: 0.8920. Min Act: -0.0000

Data Index: 939465 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 1.4480. Min Range: -1.4480

Max Act: 0.9550. Min Act: -0.0000

Data Index: 609601 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 1.4480. Min Range: -1.4480

Max Act: 0.8823. Min Act: -0.0000

Data Index: 1108296 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 1.4480. Min Range: -1.4480

Max Act: 0.9459. Min Act: -0.0000

Data Index: 629409 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 1.4480. Min Range: -1.4480

Max Act: 0.8849. Min Act: -0.0000

Data Index: 1135972 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 1.4480. Min Range: -1.4480

Max Act: 0.9901. Min Act: -0.0000

Data Index: 867153 (C4 (Web Text))

Max Activating Token Index: 911