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

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

Neuron 2033 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: 0.6064. Min Range: -0.6064

Max Act: 0.6064. Min Act: -0.0000

Data Index: 1072711 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.5552. Min Act: 0.0000

Data Index: 451584 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.5277. Min Act: -0.0000

Data Index: 1183760 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.5346. Min Act: -0.0000

Data Index: 296502 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.5106. Min Act: -0.0000

Data Index: 1103576 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.5088. Min Act: 0.0000

Data Index: 995367 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.5037. Min Act: 0.0000

Data Index: 984296 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.5216. Min Act: -0.0000

Data Index: 666185 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.5097. Min Act: -0.0000

Data Index: 113344 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.4571. Min Act: -0.0000

Data Index: 589436 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.4613. Min Act: -0.0000

Data Index: 664242 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.4503. Min Act: 0.0000

Data Index: 1122447 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.4629. Min Act: -0.0000

Data Index: 576278 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.4477. Min Act: -0.0000

Data Index: 1024850 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.4449. Min Act: 0.0000

Data Index: 62088 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.4454. Min Act: -0.0000

Data Index: 747775 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.4381. Min Act: 0.0001

Data Index: 1240714 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.4337. Min Act: -0.0000

Data Index: 109272 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.4483. Min Act: -0.0000

Data Index: 410497 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.4231. Min Act: -0.0000

Data Index: 1188444 (C4 (Web Text))

Max Activating Token Index: 206