Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3622 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2400. Min Range: -1.2400

Max Act: 1.2400. Min Act: -0.0000

Data Index: 1105937 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 1.2400. Min Range: -1.2400

Max Act: 1.0677. Min Act: -0.0000

Data Index: 1041786 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 1.2400. Min Range: -1.2400

Max Act: 1.0979. Min Act: -0.0000

Data Index: 785452 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 1.2400. Min Range: -1.2400

Max Act: 1.0615. Min Act: -0.0000

Data Index: 1014246 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 1.2400. Min Range: -1.2400

Max Act: 1.0667. Min Act: 0.0001

Data Index: 50858 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 1.2400. Min Range: -1.2400

Max Act: 1.0516. Min Act: 0.0000

Data Index: 1135313 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 1.2400. Min Range: -1.2400

Max Act: 1.0121. Min Act: -0.0000

Data Index: 177731 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 1.2400. Min Range: -1.2400

Max Act: 0.9527. Min Act: -0.0000

Data Index: 563690 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 1.2400. Min Range: -1.2400

Max Act: 0.9796. Min Act: 0.0000

Data Index: 287618 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 1.2400. Min Range: -1.2400

Max Act: 0.9511. Min Act: -0.0000

Data Index: 662683 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 1.2400. Min Range: -1.2400

Max Act: 0.9075. Min Act: -0.0000

Data Index: 860242 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 1.2400. Min Range: -1.2400

Max Act: 0.9496. Min Act: -0.0001

Data Index: 482332 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 1.2400. Min Range: -1.2400

Max Act: 0.8869. Min Act: -0.0000

Data Index: 176649 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 1.2400. Min Range: -1.2400

Max Act: 0.9143. Min Act: 0.0001

Data Index: 1037880 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 1.2400. Min Range: -1.2400

Max Act: 0.9329. Min Act: -0.0000

Data Index: 1031108 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 1.2400. Min Range: -1.2400

Max Act: 0.8869. Min Act: -0.0000

Data Index: 498340 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 1.2400. Min Range: -1.2400

Max Act: 0.8628. Min Act: -0.0000

Data Index: 985940 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 1.2400. Min Range: -1.2400

Max Act: 0.8639. Min Act: -0.0001

Data Index: 466737 (C4 (Web Text))

Max Activating Token Index: 768

Text #18

Max Range: 1.2400. Min Range: -1.2400

Max Act: 0.9151. Min Act: -0.0000

Data Index: 1230621 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 1.2400. Min Range: -1.2400

Max Act: 0.8784. Min Act: -0.0000

Data Index: 705252 (C4 (Web Text))

Max Activating Token Index: 706