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

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

Neuron 2842 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.7532. Min Act: -0.0000

Data Index: 521681 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5804. Min Act: -0.0000

Data Index: 938736 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5279. Min Act: -0.0000

Data Index: 500298 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5101. Min Act: -0.0000

Data Index: 67074 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.4961. Min Act: -0.0000

Data Index: 693468 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.4754. Min Act: -0.0000

Data Index: 404004 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.4566. Min Act: -0.0000

Data Index: 450444 (C4 (Web Text))

Max Activating Token Index: 521

Text #7

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.4693. Min Act: -0.0000

Data Index: 1163666 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.4787. Min Act: -0.0000

Data Index: 1333708 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.4482. Min Act: -0.0000

Data Index: 169537 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.4726. Min Act: -0.0000

Data Index: 1004707 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.4531. Min Act: -0.0000

Data Index: 571524 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.4483. Min Act: -0.0000

Data Index: 1217617 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.4394. Min Act: -0.0000

Data Index: 37626 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.4096. Min Act: -0.0000

Data Index: 332803 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.4284. Min Act: -0.0000

Data Index: 999168 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.4240. Min Act: -0.0000

Data Index: 471112 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.3972. Min Act: -0.0000

Data Index: 1197110 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.4310. Min Act: -0.0000

Data Index: 947954 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.4187. Min Act: -0.0000

Data Index: 364099 (C4 (Web Text))

Max Activating Token Index: 724