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

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

Neuron 5659 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: 0.2034. Min Range: -0.2034

Max Act: 0.1885. Min Act: -0.0000

Data Index: 704718 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 0.2034. Min Range: -0.2034

Max Act: 0.1970. Min Act: -0.0000

Data Index: 1110555 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 0.2034. Min Range: -0.2034

Max Act: 0.2034. Min Act: -0.0000

Data Index: 784046 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.2034. Min Range: -0.2034

Max Act: 0.1519. Min Act: -0.0000

Data Index: 1113014 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 0.2034. Min Range: -0.2034

Max Act: 0.1360. Min Act: -0.0000

Data Index: 675654 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 0.2034. Min Range: -0.2034

Max Act: 0.1457. Min Act: -0.0000

Data Index: 1195780 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 0.2034. Min Range: -0.2034

Max Act: 0.1503. Min Act: -0.0000

Data Index: 1163346 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.2034. Min Range: -0.2034

Max Act: 0.1424. Min Act: -0.0000

Data Index: 791089 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 0.2034. Min Range: -0.2034

Max Act: 0.1439. Min Act: -0.0000

Data Index: 1202694 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 0.2034. Min Range: -0.2034

Max Act: 0.1364. Min Act: -0.0000

Data Index: 32124 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 0.2034. Min Range: -0.2034

Max Act: 0.1339. Min Act: -0.0000

Data Index: 784402 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 0.2034. Min Range: -0.2034

Max Act: 0.1333. Min Act: -0.0000

Data Index: 378659 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 0.2034. Min Range: -0.2034

Max Act: 0.1208. Min Act: -0.0000

Data Index: 380362 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 0.2034. Min Range: -0.2034

Max Act: 0.1371. Min Act: -0.0000

Data Index: 1346242 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 0.2034. Min Range: -0.2034

Max Act: 0.1254. Min Act: -0.0000

Data Index: 252321 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 0.2034. Min Range: -0.2034

Max Act: 0.1273. Min Act: -0.0000

Data Index: 449170 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 0.2034. Min Range: -0.2034

Max Act: 0.1338. Min Act: -0.0000

Data Index: 981023 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 0.2034. Min Range: -0.2034

Max Act: 0.1359. Min Act: -0.0000

Data Index: 1179595 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 0.2034. Min Range: -0.2034

Max Act: 0.1307. Min Act: -0.0000

Data Index: 1254277 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.2034. Min Range: -0.2034

Max Act: 0.1241. Min Act: -0.0000

Data Index: 632671 (C4 (Web Text))

Max Activating Token Index: 950