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

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

Neuron 2815 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: 0.8199. Min Range: -0.8199

Max Act: 0.8199. Min Act: -0.0000

Data Index: 907149 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.6602. Min Act: -0.0000

Data Index: 1622104 (Python Code)

Max Activating Token Index: 776

Text #2

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.5405. Min Act: -0.0000

Data Index: 1100163 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.5458. Min Act: -0.0000

Data Index: 631911 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.5543. Min Act: -0.0000

Data Index: 44556 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.5644. Min Act: -0.0000

Data Index: 1275703 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.5060. Min Act: -0.0000

Data Index: 1522400 (Python Code)

Max Activating Token Index: 841

Text #7

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.5630. Min Act: -0.0000

Data Index: 1287135 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.5517. Min Act: -0.0000

Data Index: 133699 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.5581. Min Act: -0.0000

Data Index: 1647346 (Python Code)

Max Activating Token Index: 150

Text #10

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.5281. Min Act: -0.0000

Data Index: 1259670 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.5399. Min Act: -0.0000

Data Index: 101058 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.5100. Min Act: -0.0000

Data Index: 1568525 (Python Code)

Max Activating Token Index: 370

Text #13

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.5561. Min Act: -0.0000

Data Index: 1221224 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.5138. Min Act: -0.0000

Data Index: 381148 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.5048. Min Act: -0.0000

Data Index: 1463750 (Python Code)

Max Activating Token Index: 554

Text #16

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.5331. Min Act: -0.0000

Data Index: 233960 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.4635. Min Act: -0.0000

Data Index: 1216731 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.5071. Min Act: -0.0000

Data Index: 1163343 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.4899. Min Act: -0.0000

Data Index: 35214 (C4 (Web Text))

Max Activating Token Index: 659