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

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

Neuron 5537 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1485. Min Range: -0.1485

Max Act: 0.1485. Min Act: -0.0001

Data Index: 873467 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.1485. Min Range: -0.1485

Max Act: 0.1344. Min Act: -0.0001

Data Index: 920287 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 0.1485. Min Range: -0.1485

Max Act: 0.1315. Min Act: -0.0001

Data Index: 1376866 (Python Code)

Max Activating Token Index: 676

Text #3

Max Range: 0.1485. Min Range: -0.1485

Max Act: 0.1178. Min Act: -0.0001

Data Index: 1570786 (Python Code)

Max Activating Token Index: 807

Text #4

Max Range: 0.1485. Min Range: -0.1485

Max Act: 0.1235. Min Act: -0.0001

Data Index: 1588971 (Python Code)

Max Activating Token Index: 792

Text #5

Max Range: 0.1485. Min Range: -0.1485

Max Act: 0.1234. Min Act: -0.0001

Data Index: 1387550 (Python Code)

Max Activating Token Index: 101

Text #6

Max Range: 0.1485. Min Range: -0.1485

Max Act: 0.1156. Min Act: -0.0001

Data Index: 1083157 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 0.1485. Min Range: -0.1485

Max Act: 0.1146. Min Act: -0.0001

Data Index: 588067 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 0.1485. Min Range: -0.1485

Max Act: 0.1249. Min Act: -0.0001

Data Index: 1538503 (Python Code)

Max Activating Token Index: 178

Text #9

Max Range: 0.1485. Min Range: -0.1485

Max Act: 0.1211. Min Act: -0.0001

Data Index: 1532902 (Python Code)

Max Activating Token Index: 18

Text #10

Max Range: 0.1485. Min Range: -0.1485

Max Act: 0.1244. Min Act: -0.0001

Data Index: 1470890 (Python Code)

Max Activating Token Index: 608

Text #11

Max Range: 0.1485. Min Range: -0.1485

Max Act: 0.1242. Min Act: -0.0001

Data Index: 1527507 (Python Code)

Max Activating Token Index: 676

Text #12

Max Range: 0.1485. Min Range: -0.1485

Max Act: 0.1114. Min Act: -0.0001

Data Index: 1406937 (Python Code)

Max Activating Token Index: 165

Text #13

Max Range: 0.1485. Min Range: -0.1485

Max Act: 0.1183. Min Act: -0.0001

Data Index: 1648511 (Python Code)

Max Activating Token Index: 438

Text #14

Max Range: 0.1485. Min Range: -0.1485

Max Act: 0.1108. Min Act: -0.0001

Data Index: 1040217 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 0.1485. Min Range: -0.1485

Max Act: 0.1165. Min Act: -0.0001

Data Index: 382895 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 0.1485. Min Range: -0.1485

Max Act: 0.1131. Min Act: -0.0001

Data Index: 1451007 (Python Code)

Max Activating Token Index: 962

Text #17

Max Range: 0.1485. Min Range: -0.1485

Max Act: 0.1098. Min Act: -0.0001

Data Index: 914998 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 0.1485. Min Range: -0.1485

Max Act: 0.1191. Min Act: -0.0001

Data Index: 1582259 (Python Code)

Max Activating Token Index: 898

Text #19

Max Range: 0.1485. Min Range: -0.1485

Max Act: 0.1171. Min Act: -0.0001

Data Index: 1082996 (C4 (Web Text))

Max Activating Token Index: 311