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

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

Neuron 2225 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0576. Min Range: -1.0576

Max Act: 1.0576. Min Act: -0.0000

Data Index: 382735 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 1.0576. Min Range: -1.0576

Max Act: 1.0576. Min Act: -0.0000

Data Index: 942663 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.9527. Min Act: -0.0000

Data Index: 249894 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.9291. Min Act: -0.0000

Data Index: 1308500 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.9420. Min Act: -0.0000

Data Index: 603445 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.9439. Min Act: -0.0000

Data Index: 23257 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.9710. Min Act: -0.0000

Data Index: 976358 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.9595. Min Act: -0.0000

Data Index: 136014 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.9608. Min Act: -0.0000

Data Index: 377530 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.9241. Min Act: -0.0001

Data Index: 307934 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.9167. Min Act: -0.0000

Data Index: 1127457 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.9176. Min Act: -0.0000

Data Index: 1012304 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.8781. Min Act: -0.0000

Data Index: 460175 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.8820. Min Act: -0.0000

Data Index: 1332857 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.9220. Min Act: -0.0000

Data Index: 1154142 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.8987. Min Act: -0.0000

Data Index: 190381 (C4 (Web Text))

Max Activating Token Index: 573

Text #16

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.8243. Min Act: -0.0000

Data Index: 1030815 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.9151. Min Act: -0.0000

Data Index: 306600 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.9391. Min Act: -0.0000

Data Index: 69539 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.8853. Min Act: -0.0000

Data Index: 585950 (C4 (Web Text))

Max Activating Token Index: 77