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

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

Neuron 332 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1683. Min Range: -1.1683

Max Act: 1.1683. Min Act: -0.0001

Data Index: 384576 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 1.1683. Min Range: -1.1683

Max Act: 1.0702. Min Act: -0.0001

Data Index: 230034 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.9953. Min Act: -0.0001

Data Index: 142203 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.9400. Min Act: -0.0001

Data Index: 1163171 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.9796. Min Act: -0.0001

Data Index: 519600 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.9640. Min Act: -0.0001

Data Index: 539029 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.9260. Min Act: -0.0001

Data Index: 165642 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.9534. Min Act: -0.0001

Data Index: 148117 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.9208. Min Act: -0.0001

Data Index: 1118423 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.9206. Min Act: -0.0001

Data Index: 422107 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.9331. Min Act: -0.0001

Data Index: 818616 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.9475. Min Act: -0.0001

Data Index: 14357 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.8967. Min Act: -0.0001

Data Index: 449010 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.8720. Min Act: -0.0001

Data Index: 312613 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.8954. Min Act: -0.0001

Data Index: 1302207 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.8914. Min Act: -0.0001

Data Index: 104180 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.8739. Min Act: -0.0001

Data Index: 672258 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.8704. Min Act: -0.0001

Data Index: 537104 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.8981. Min Act: -0.0001

Data Index: 179611 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.8641. Min Act: -0.0001

Data Index: 922866 (C4 (Web Text))

Max Activating Token Index: 49