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

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

Neuron 442 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: 0.7734. Min Range: -0.7734

Max Act: 0.7734. Min Act: -0.0001

Data Index: 446511 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.5821. Min Act: -0.0001

Data Index: 326553 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.4901. Min Act: -0.0001

Data Index: 375298 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.5062. Min Act: -0.0001

Data Index: 915407 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.5343. Min Act: -0.0001

Data Index: 1165323 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.5119. Min Act: -0.0001

Data Index: 152185 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.4576. Min Act: -0.0001

Data Index: 342875 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.4430. Min Act: -0.0001

Data Index: 1194852 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.4294. Min Act: -0.0001

Data Index: 136063 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.4507. Min Act: -0.0001

Data Index: 1057572 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.4186. Min Act: -0.0001

Data Index: 943986 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.4322. Min Act: -0.0001

Data Index: 1275271 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.4271. Min Act: -0.0001

Data Index: 342841 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.4094. Min Act: -0.0001

Data Index: 1162185 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.4071. Min Act: -0.0001

Data Index: 528971 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.4146. Min Act: -0.0001

Data Index: 1306170 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.4253. Min Act: -0.0001

Data Index: 580218 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.4047. Min Act: -0.0001

Data Index: 141393 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.3785. Min Act: -0.0001

Data Index: 665885 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.3748. Min Act: -0.0001

Data Index: 151645 (C4 (Web Text))

Max Activating Token Index: 354