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

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

Neuron 1432 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1446. Min Range: -1.1446

Max Act: 1.1446. Min Act: -0.0000

Data Index: 576063 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 1.1446. Min Range: -1.1446

Max Act: 1.1343. Min Act: -0.0000

Data Index: 701427 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 1.1446. Min Range: -1.1446

Max Act: 1.0469. Min Act: -0.0000

Data Index: 55091 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.9735. Min Act: -0.0000

Data Index: 1179561 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.9185. Min Act: -0.0000

Data Index: 194296 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.8381. Min Act: -0.0000

Data Index: 628634 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.9003. Min Act: -0.0000

Data Index: 59570 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.8931. Min Act: -0.0000

Data Index: 254829 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.8806. Min Act: -0.0000

Data Index: 723907 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.8082. Min Act: -0.0000

Data Index: 428437 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.8356. Min Act: -0.0000

Data Index: 1182853 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.8285. Min Act: -0.0000

Data Index: 397656 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.8806. Min Act: -0.0000

Data Index: 1067142 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.7952. Min Act: -0.0000

Data Index: 203864 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.8248. Min Act: -0.0000

Data Index: 93982 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.7314. Min Act: -0.0000

Data Index: 971736 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.8273. Min Act: -0.0000

Data Index: 599775 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.7667. Min Act: -0.0000

Data Index: 404542 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.7855. Min Act: -0.0000

Data Index: 1396319 (Python Code)

Max Activating Token Index: 381

Text #19

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.7564. Min Act: -0.0000

Data Index: 577757 (C4 (Web Text))

Max Activating Token Index: 401