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

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

Neuron 1941 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.4636. Min Act: -0.0001

Data Index: 790805 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.4108. Min Act: -0.0001

Data Index: 742235 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.4315. Min Act: -0.0002

Data Index: 495679 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3813. Min Act: -0.0001

Data Index: 932451 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.4153. Min Act: -0.0002

Data Index: 703360 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3745. Min Act: -0.0002

Data Index: 160010 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.4289. Min Act: -0.0001

Data Index: 792416 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.4034. Min Act: -0.0001

Data Index: 1582041 (Python Code)

Max Activating Token Index: 269

Text #8

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.4131. Min Act: -0.0001

Data Index: 1228811 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.4410. Min Act: -0.0002

Data Index: 187282 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.4107. Min Act: -0.0002

Data Index: 146347 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.4257. Min Act: -0.0001

Data Index: 59964 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3968. Min Act: -0.0002

Data Index: 608337 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3909. Min Act: -0.0002

Data Index: 242085 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.4213. Min Act: -0.0001

Data Index: 759262 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3916. Min Act: -0.0002

Data Index: 959570 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3860. Min Act: -0.0002

Data Index: 974155 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3881. Min Act: -0.0001

Data Index: 859522 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3976. Min Act: -0.0001

Data Index: 325574 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3685. Min Act: -0.0001

Data Index: 999073 (C4 (Web Text))

Max Activating Token Index: 230