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

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

Neuron 5430 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1818. Min Act: -0.0000

Data Index: 1521497 (Python Code)

Max Activating Token Index: 404

Text #1

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1304. Min Act: -0.0000

Data Index: 415509 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1382. Min Act: -0.0000

Data Index: 530544 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1449. Min Act: -0.0000

Data Index: 1423174 (Python Code)

Max Activating Token Index: 954

Text #4

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1249. Min Act: -0.0000

Data Index: 1391450 (Python Code)

Max Activating Token Index: 788

Text #5

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1316. Min Act: -0.0000

Data Index: 1374683 (Python Code)

Max Activating Token Index: 369

Text #6

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1364. Min Act: -0.0000

Data Index: 658520 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1340. Min Act: -0.0000

Data Index: 1385539 (Python Code)

Max Activating Token Index: 951

Text #8

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1158. Min Act: -0.0000

Data Index: 1642580 (Python Code)

Max Activating Token Index: 452

Text #9

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1250. Min Act: -0.0000

Data Index: 1461702 (Python Code)

Max Activating Token Index: 330

Text #10

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1218. Min Act: -0.0000

Data Index: 1569422 (Python Code)

Max Activating Token Index: 347

Text #11

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1328. Min Act: -0.0000

Data Index: 1481502 (Python Code)

Max Activating Token Index: 788

Text #12

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1180. Min Act: -0.0000

Data Index: 1579464 (Python Code)

Max Activating Token Index: 783

Text #13

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1160. Min Act: -0.0000

Data Index: 1563460 (Python Code)

Max Activating Token Index: 786

Text #14

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1088. Min Act: -0.0000

Data Index: 1367848 (Python Code)

Max Activating Token Index: 250

Text #15

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1544262 (Python Code)

Max Activating Token Index: 868

Text #16

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1107. Min Act: -0.0000

Data Index: 1083782 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1151. Min Act: -0.0000

Data Index: 1096659 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1076. Min Act: -0.0000

Data Index: 1407446 (Python Code)

Max Activating Token Index: 838

Text #19

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1180. Min Act: -0.0000

Data Index: 610056 (C4 (Web Text))

Max Activating Token Index: 786