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

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

Neuron 1387 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.5208. Min Act: -0.0000

Data Index: 941524 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.4924. Min Act: -0.0000

Data Index: 943987 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.4790. Min Act: -0.0000

Data Index: 124611 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.5116. Min Act: -0.0000

Data Index: 831585 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.4613. Min Act: -0.0000

Data Index: 902456 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.4686. Min Act: -0.0000

Data Index: 1081821 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.4951. Min Act: -0.0000

Data Index: 684557 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.4621. Min Act: -0.0000

Data Index: 112353 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.4395. Min Act: -0.0000

Data Index: 35011 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.3697. Min Act: -0.0000

Data Index: 569939 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.3888. Min Act: -0.0000

Data Index: 699211 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.4814. Min Act: -0.0000

Data Index: 264881 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.4333. Min Act: -0.0000

Data Index: 890559 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.4099. Min Act: -0.0000

Data Index: 664348 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.4059. Min Act: -0.0000

Data Index: 942860 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.4175. Min Act: -0.0000

Data Index: 527870 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.3365. Min Act: -0.0000

Data Index: 1195494 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.4406. Min Act: -0.0000

Data Index: 656715 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.4135. Min Act: -0.0000

Data Index: 1195623 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.4278. Min Act: -0.0000

Data Index: 447814 (C4 (Web Text))

Max Activating Token Index: 504