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

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

Neuron 5056 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: 0.9394. Min Range: -0.9394

Max Act: 0.9394. Min Act: -0.0000

Data Index: 852157 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.1754. Min Act: -0.0000

Data Index: 319736 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.1542. Min Act: -0.0000

Data Index: 1575356 (Python Code)

Max Activating Token Index: 742

Text #3

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.1538. Min Act: -0.0000

Data Index: 602580 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.1407. Min Act: -0.0000

Data Index: 1156791 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.1181. Min Act: -0.0000

Data Index: 1051046 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.1342. Min Act: -0.0000

Data Index: 1509297 (Python Code)

Max Activating Token Index: 154

Text #7

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.1233. Min Act: -0.0000

Data Index: 792040 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.1319. Min Act: -0.0000

Data Index: 1560203 (Python Code)

Max Activating Token Index: 809

Text #9

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.1319. Min Act: -0.0000

Data Index: 1579113 (Python Code)

Max Activating Token Index: 436

Text #10

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.1676. Min Act: -0.0000

Data Index: 489809 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.1066. Min Act: -0.0000

Data Index: 1478258 (Python Code)

Max Activating Token Index: 584

Text #12

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.1102. Min Act: -0.0000

Data Index: 1437664 (Python Code)

Max Activating Token Index: 669

Text #13

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.1034. Min Act: -0.0000

Data Index: 1453116 (Python Code)

Max Activating Token Index: 538

Text #14

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.1185. Min Act: -0.0000

Data Index: 298084 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.1152. Min Act: -0.0000

Data Index: 193298 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.1031. Min Act: -0.0000

Data Index: 284729 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.0889. Min Act: -0.0000

Data Index: 1295842 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.1033. Min Act: -0.0000

Data Index: 1305401 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.1068. Min Act: -0.0000

Data Index: 454208 (C4 (Web Text))

Max Activating Token Index: 46