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

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

Neuron 3609 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1381. Min Range: -1.1381

Max Act: 1.1381. Min Act: -0.0000

Data Index: 912969 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 1.1381. Min Range: -1.1381

Max Act: 1.0890. Min Act: -0.0001

Data Index: 330361 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.9988. Min Act: -0.0000

Data Index: 1072027 (C4 (Web Text))

Max Activating Token Index: 325

Text #3

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.9374. Min Act: -0.0000

Data Index: 604051 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.9155. Min Act: -0.0001

Data Index: 1346821 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.9224. Min Act: -0.0000

Data Index: 710409 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.9240. Min Act: -0.0001

Data Index: 1337849 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.9436. Min Act: -0.0000

Data Index: 1355385 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.8209. Min Act: -0.0000

Data Index: 266616 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.8504. Min Act: -0.0001

Data Index: 447559 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.7983. Min Act: -0.0000

Data Index: 350463 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.8472. Min Act: -0.0000

Data Index: 284143 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.8634. Min Act: -0.0001

Data Index: 1197946 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.8196. Min Act: -0.0000

Data Index: 267193 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.8303. Min Act: -0.0001

Data Index: 112535 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.7725. Min Act: -0.0000

Data Index: 516329 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.7930. Min Act: -0.0000

Data Index: 184059 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.7863. Min Act: -0.0000

Data Index: 1202469 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.7414. Min Act: -0.0000

Data Index: 101044 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.8150. Min Act: -0.0000

Data Index: 727993 (C4 (Web Text))

Max Activating Token Index: 368