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

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

Neuron 6032 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6550. Min Range: -1.6550

Max Act: 1.6550. Min Act: 0.0000

Data Index: 775797 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 1.6550. Min Range: -1.6550

Max Act: 1.1226. Min Act: -0.0000

Data Index: 1598269 (Python Code)

Max Activating Token Index: 538

Text #2

Max Range: 1.6550. Min Range: -1.6550

Max Act: 1.1002. Min Act: -0.0000

Data Index: 241703 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 1.6550. Min Range: -1.6550

Max Act: 1.1331. Min Act: -0.0000

Data Index: 47941 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 1.6550. Min Range: -1.6550

Max Act: 0.9656. Min Act: -0.0000

Data Index: 1611350 (Python Code)

Max Activating Token Index: 815

Text #5

Max Range: 1.6550. Min Range: -1.6550

Max Act: 0.8919. Min Act: -0.0000

Data Index: 1605580 (Python Code)

Max Activating Token Index: 369

Text #6

Max Range: 1.6550. Min Range: -1.6550

Max Act: 0.8465. Min Act: -0.0000

Data Index: 758194 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 1.6550. Min Range: -1.6550

Max Act: 0.7869. Min Act: -0.0000

Data Index: 1022851 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 1.6550. Min Range: -1.6550

Max Act: 0.7510. Min Act: -0.0000

Data Index: 532497 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 1.6550. Min Range: -1.6550

Max Act: 0.7289. Min Act: -0.0000

Data Index: 1554289 (Python Code)

Max Activating Token Index: 222

Text #10

Max Range: 1.6550. Min Range: -1.6550

Max Act: 0.7255. Min Act: -0.0000

Data Index: 1047792 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 1.6550. Min Range: -1.6550

Max Act: 0.7172. Min Act: -0.0000

Data Index: 967520 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 1.6550. Min Range: -1.6550

Max Act: 0.7041. Min Act: -0.0000

Data Index: 1620381 (Python Code)

Max Activating Token Index: 2

Text #13

Max Range: 1.6550. Min Range: -1.6550

Max Act: 0.6442. Min Act: -0.0000

Data Index: 1419651 (Python Code)

Max Activating Token Index: 181

Text #14

Max Range: 1.6550. Min Range: -1.6550

Max Act: 0.6948. Min Act: -0.0000

Data Index: 1281933 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 1.6550. Min Range: -1.6550

Max Act: 0.6246. Min Act: -0.0000

Data Index: 101526 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 1.6550. Min Range: -1.6550

Max Act: 0.6683. Min Act: -0.0000

Data Index: 334939 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 1.6550. Min Range: -1.6550

Max Act: 0.6470. Min Act: -0.0000

Data Index: 961705 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 1.6550. Min Range: -1.6550

Max Act: 0.6382. Min Act: 0.0000

Data Index: 879618 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 1.6550. Min Range: -1.6550

Max Act: 0.6150. Min Act: -0.0000

Data Index: 705434 (C4 (Web Text))

Max Activating Token Index: 845