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

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

Neuron 2197 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.3168. Min Act: -0.0001

Data Index: 173414 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.3184. Min Act: -0.0001

Data Index: 460749 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.3282. Min Act: -0.0001

Data Index: 1297394 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2932. Min Act: -0.0001

Data Index: 1627355 (Python Code)

Max Activating Token Index: 979

Text #4

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2935. Min Act: -0.0001

Data Index: 1055081 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2982. Min Act: -0.0001

Data Index: 1427446 (Python Code)

Max Activating Token Index: 982

Text #6

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.3091. Min Act: -0.0001

Data Index: 1608943 (Python Code)

Max Activating Token Index: 1010

Text #7

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.3093. Min Act: -0.0001

Data Index: 1519519 (Python Code)

Max Activating Token Index: 999

Text #8

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2798. Min Act: -0.0000

Data Index: 1120661 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2738. Min Act: -0.0001

Data Index: 1142377 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2793. Min Act: -0.0001

Data Index: 728131 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2730. Min Act: -0.0001

Data Index: 1516412 (Python Code)

Max Activating Token Index: 967

Text #12

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2995. Min Act: -0.0001

Data Index: 1345436 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2800. Min Act: -0.0000

Data Index: 1168468 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2731. Min Act: -0.0001

Data Index: 1652508 (Python Code)

Max Activating Token Index: 954

Text #15

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2787. Min Act: -0.0001

Data Index: 1591299 (Python Code)

Max Activating Token Index: 1020

Text #16

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2599. Min Act: -0.0001

Data Index: 1429709 (Python Code)

Max Activating Token Index: 931

Text #17

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2731. Min Act: -0.0001

Data Index: 1600844 (Python Code)

Max Activating Token Index: 877

Text #18

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2762. Min Act: -0.0001

Data Index: 1620396 (Python Code)

Max Activating Token Index: 917

Text #19

Max Range: 0.3282. Min Range: -0.3282

Max Act: 0.2686. Min Act: -0.0001

Data Index: 1650768 (Python Code)

Max Activating Token Index: 954