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

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

Neuron 783 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0355. Min Act: -0.0001

Data Index: 1484713 (Python Code)

Max Activating Token Index: 554

Text #1

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0335. Min Act: -0.0001

Data Index: 1396467 (Python Code)

Max Activating Token Index: 634

Text #2

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0338. Min Act: -0.0001

Data Index: 797944 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0330. Min Act: -0.0001

Data Index: 1448460 (Python Code)

Max Activating Token Index: 639

Text #4

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0330. Min Act: -0.0001

Data Index: 709709 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0330. Min Act: -0.0001

Data Index: 1280546 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0326. Min Act: -0.0001

Data Index: 707950 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0323. Min Act: -0.0001

Data Index: 272066 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0322. Min Act: -0.0000

Data Index: 983406 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0318. Min Act: -0.0001

Data Index: 1611637 (Python Code)

Max Activating Token Index: 559

Text #10

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0309. Min Act: -0.0001

Data Index: 1097792 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0320. Min Act: -0.0001

Data Index: 33331 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0316. Min Act: -0.0001

Data Index: 1310722 (C4 (Web Text))

Max Activating Token Index: 789

Text #13

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0316. Min Act: -0.0001

Data Index: 307271 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0312. Min Act: -0.0001

Data Index: 658560 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0302. Min Act: -0.0001

Data Index: 500697 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0298. Min Act: -0.0001

Data Index: 602591 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0301. Min Act: -0.0001

Data Index: 511223 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0300. Min Act: -0.0001

Data Index: 1128054 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0297. Min Act: -0.0001

Data Index: 121708 (C4 (Web Text))

Max Activating Token Index: 172