Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1181 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4299. Min Range: -1.4299

Max Act: 1.4299. Min Act: -0.0001

Data Index: 732266 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 1.4299. Min Range: -1.4299

Max Act: 1.4214. Min Act: -0.0001

Data Index: 886589 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 1.4299. Min Range: -1.4299

Max Act: 1.3421. Min Act: -0.0001

Data Index: 396902 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 1.4299. Min Range: -1.4299

Max Act: 1.2942. Min Act: -0.0001

Data Index: 1325927 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 1.4299. Min Range: -1.4299

Max Act: 1.3100. Min Act: -0.0001

Data Index: 1319318 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 1.4299. Min Range: -1.4299

Max Act: 1.2359. Min Act: -0.0001

Data Index: 1653757 (Python Code)

Max Activating Token Index: 153

Text #6

Max Range: 1.4299. Min Range: -1.4299

Max Act: 1.1417. Min Act: -0.0001

Data Index: 1597239 (Python Code)

Max Activating Token Index: 805

Text #7

Max Range: 1.4299. Min Range: -1.4299

Max Act: 1.1754. Min Act: -0.0001

Data Index: 511081 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 1.4299. Min Range: -1.4299

Max Act: 1.1113. Min Act: -0.0001

Data Index: 1575063 (Python Code)

Max Activating Token Index: 1020

Text #9

Max Range: 1.4299. Min Range: -1.4299

Max Act: 1.1405. Min Act: -0.0001

Data Index: 599546 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 1.4299. Min Range: -1.4299

Max Act: 1.1010. Min Act: -0.0001

Data Index: 1088402 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 1.4299. Min Range: -1.4299

Max Act: 1.1196. Min Act: -0.0001

Data Index: 1629110 (Python Code)

Max Activating Token Index: 581

Text #12

Max Range: 1.4299. Min Range: -1.4299

Max Act: 1.1198. Min Act: -0.0001

Data Index: 1618763 (Python Code)

Max Activating Token Index: 105

Text #13

Max Range: 1.4299. Min Range: -1.4299

Max Act: 1.0849. Min Act: -0.0001

Data Index: 1377856 (Python Code)

Max Activating Token Index: 118

Text #14

Max Range: 1.4299. Min Range: -1.4299

Max Act: 1.1029. Min Act: -0.0001

Data Index: 1089501 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 1.4299. Min Range: -1.4299

Max Act: 1.0919. Min Act: -0.0001

Data Index: 1493574 (Python Code)

Max Activating Token Index: 45

Text #16

Max Range: 1.4299. Min Range: -1.4299

Max Act: 1.0530. Min Act: -0.0001

Data Index: 1351847 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 1.4299. Min Range: -1.4299

Max Act: 1.0138. Min Act: -0.0001

Data Index: 246834 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 1.4299. Min Range: -1.4299

Max Act: 1.1047. Min Act: -0.0001

Data Index: 1406303 (Python Code)

Max Activating Token Index: 828

Text #19

Max Range: 1.4299. Min Range: -1.4299

Max Act: 1.0954. Min Act: -0.0001

Data Index: 1121423 (C4 (Web Text))

Max Activating Token Index: 590