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

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

Neuron 2647 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.5545. Min Act: -0.0001

Data Index: 412942 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.5145. Min Act: -0.0001

Data Index: 471421 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.5136. Min Act: -0.0001

Data Index: 1173455 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.4934. Min Act: -0.0001

Data Index: 146535 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.4844. Min Act: -0.0000

Data Index: 898129 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.4934. Min Act: -0.0000

Data Index: 1030723 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.5070. Min Act: -0.0001

Data Index: 212835 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.4806. Min Act: -0.0000

Data Index: 1289915 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.4687. Min Act: -0.0001

Data Index: 883195 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.4507. Min Act: -0.0000

Data Index: 287597 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.4503. Min Act: -0.0001

Data Index: 550925 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.4648. Min Act: -0.0001

Data Index: 487374 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.4429. Min Act: -0.0001

Data Index: 1074209 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.4432. Min Act: -0.0001

Data Index: 1128596 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.4234. Min Act: -0.0001

Data Index: 1109414 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.4530. Min Act: -0.0000

Data Index: 1186915 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.4643. Min Act: -0.0001

Data Index: 405155 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.4635. Min Act: -0.0000

Data Index: 1065114 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.4481. Min Act: -0.0000

Data Index: 954029 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 0.5545. Min Range: -0.5545

Max Act: 0.4329. Min Act: -0.0001

Data Index: 1047168 (C4 (Web Text))

Max Activating Token Index: 441