Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4146 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.9964. Min Range: -5.9964

Max Act: 5.9964. Min Act: -0.0000

Data Index: 1336400 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 5.9964. Min Range: -5.9964

Max Act: 5.6517. Min Act: -0.0000

Data Index: 815168 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 5.9964. Min Range: -5.9964

Max Act: 5.4126. Min Act: -0.0000

Data Index: 440547 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 5.9964. Min Range: -5.9964

Max Act: 5.3959. Min Act: -0.0000

Data Index: 637114 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 5.9964. Min Range: -5.9964

Max Act: 5.1954. Min Act: -0.0000

Data Index: 899985 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 5.9964. Min Range: -5.9964

Max Act: 5.2502. Min Act: -0.0000

Data Index: 42348 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 5.9964. Min Range: -5.9964

Max Act: 5.0142. Min Act: -0.0000

Data Index: 1165888 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 5.9964. Min Range: -5.9964

Max Act: 5.0993. Min Act: -0.0000

Data Index: 5832 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 5.9964. Min Range: -5.9964

Max Act: 4.7817. Min Act: -0.0000

Data Index: 461473 (C4 (Web Text))

Max Activating Token Index: 999

Text #9

Max Range: 5.9964. Min Range: -5.9964

Max Act: 4.7191. Min Act: -0.0000

Data Index: 333291 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 5.9964. Min Range: -5.9964

Max Act: 4.5378. Min Act: -0.0000

Data Index: 929035 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 5.9964. Min Range: -5.9964

Max Act: 4.5020. Min Act: -0.0000

Data Index: 973314 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 5.9964. Min Range: -5.9964

Max Act: 4.5636. Min Act: -0.0000

Data Index: 573510 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 5.9964. Min Range: -5.9964

Max Act: 4.3657. Min Act: -0.0000

Data Index: 1232576 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 5.9964. Min Range: -5.9964

Max Act: 4.1198. Min Act: -0.0000

Data Index: 286314 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 5.9964. Min Range: -5.9964

Max Act: 4.1110. Min Act: -0.0000

Data Index: 923404 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 5.9964. Min Range: -5.9964

Max Act: 4.3463. Min Act: -0.0000

Data Index: 878847 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 5.9964. Min Range: -5.9964

Max Act: 4.1554. Min Act: -0.0000

Data Index: 370701 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 5.9964. Min Range: -5.9964

Max Act: 4.2700. Min Act: -0.0000

Data Index: 508918 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 5.9964. Min Range: -5.9964

Max Act: 4.2546. Min Act: -0.0000

Data Index: 730500 (C4 (Web Text))

Max Activating Token Index: 944