Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 959 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0404. Min Act: -0.0006

Data Index: 568182 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0339. Min Act: -0.0006

Data Index: 420138 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0339. Min Act: -0.0006

Data Index: 405574 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0336. Min Act: -0.0006

Data Index: 209702 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0306. Min Act: -0.0006

Data Index: 1561279 (Python Code)

Max Activating Token Index: 304

Text #5

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0320. Min Act: -0.0006

Data Index: 1408307 (Python Code)

Max Activating Token Index: 484

Text #6

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0309. Min Act: -0.0006

Data Index: 1435796 (Python Code)

Max Activating Token Index: 294

Text #7

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0295. Min Act: -0.0006

Data Index: 1451603 (Python Code)

Max Activating Token Index: 200

Text #8

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0293. Min Act: -0.0006

Data Index: 759560 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0287. Min Act: -0.0006

Data Index: 1365388 (Python Code)

Max Activating Token Index: 531

Text #10

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0278. Min Act: -0.0006

Data Index: 1538198 (Python Code)

Max Activating Token Index: 1012

Text #11

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0288. Min Act: -0.0006

Data Index: 798116 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0290. Min Act: -0.0006

Data Index: 13065 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0293. Min Act: -0.0006

Data Index: 1471071 (Python Code)

Max Activating Token Index: 761

Text #14

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0288. Min Act: -0.0006

Data Index: 1541551 (Python Code)

Max Activating Token Index: 194

Text #15

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0271. Min Act: -0.0006

Data Index: 1609654 (Python Code)

Max Activating Token Index: 709

Text #16

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0290. Min Act: -0.0006

Data Index: 1084741 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0283. Min Act: -0.0006

Data Index: 1094053 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0280. Min Act: -0.0006

Data Index: 1515109 (Python Code)

Max Activating Token Index: 191

Text #19

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0295. Min Act: -0.0006

Data Index: 1622571 (Python Code)

Max Activating Token Index: 416