Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1676 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2288. Min Act: -0.0001

Data Index: 907912 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2274. Min Act: -0.0001

Data Index: 718123 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2398. Min Act: -0.0001

Data Index: 747086 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2409. Min Act: -0.0001

Data Index: 450851 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2335. Min Act: -0.0001

Data Index: 1108284 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2279. Min Act: -0.0001

Data Index: 1105525 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2215. Min Act: -0.0001

Data Index: 866269 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2446. Min Act: -0.0001

Data Index: 1024144 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2344. Min Act: -0.0001

Data Index: 88502 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2359. Min Act: -0.0001

Data Index: 1046692 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2081. Min Act: -0.0001

Data Index: 829113 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2141. Min Act: -0.0001

Data Index: 482070 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2234. Min Act: -0.0001

Data Index: 805107 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2226. Min Act: -0.0001

Data Index: 1315749 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2088. Min Act: -0.0001

Data Index: 192325 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2311. Min Act: -0.0001

Data Index: 525147 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2176. Min Act: -0.0001

Data Index: 627384 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2139. Min Act: -0.0001

Data Index: 708409 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2133. Min Act: -0.0001

Data Index: 897347 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2091. Min Act: -0.0001

Data Index: 761213 (C4 (Web Text))

Max Activating Token Index: 634