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

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

Neuron 5335 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.8942. Min Act: -0.0001

Data Index: 44527 (C4 (Web Text))

Max Activating Token Index: 807

Text #1

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.8574. Min Act: -0.0001

Data Index: 157756 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.8444. Min Act: -0.0001

Data Index: 88393 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.8211. Min Act: -0.0001

Data Index: 822362 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.7589. Min Act: -0.0001

Data Index: 1487711 (Python Code)

Max Activating Token Index: 743

Text #5

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.8057. Min Act: -0.0001

Data Index: 1594468 (Python Code)

Max Activating Token Index: 898

Text #6

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.7696. Min Act: -0.0001

Data Index: 1430628 (Python Code)

Max Activating Token Index: 15

Text #7

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.7579. Min Act: -0.0001

Data Index: 1416340 (Python Code)

Max Activating Token Index: 15

Text #8

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.7327. Min Act: -0.0001

Data Index: 1103759 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.6963. Min Act: -0.0001

Data Index: 1244687 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.6612. Min Act: -0.0001

Data Index: 492131 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.7238. Min Act: -0.0001

Data Index: 931638 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.7278. Min Act: -0.0001

Data Index: 323040 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.6814. Min Act: -0.0001

Data Index: 687270 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.6903. Min Act: -0.0001

Data Index: 1625166 (Python Code)

Max Activating Token Index: 267

Text #15

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.7234. Min Act: -0.0001

Data Index: 1616207 (Python Code)

Max Activating Token Index: 16

Text #16

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.6692. Min Act: -0.0001

Data Index: 990412 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.6719. Min Act: -0.0001

Data Index: 654717 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.6392. Min Act: -0.0001

Data Index: 1607786 (Python Code)

Max Activating Token Index: 801

Text #19

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.5934. Min Act: -0.0001

Data Index: 815894 (C4 (Web Text))

Max Activating Token Index: 737