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

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

Neuron 3601 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: 0.4742. Min Range: -0.4742

Max Act: 0.4663. Min Act: -0.0002

Data Index: 650001 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4742. Min Act: -0.0001

Data Index: 9577 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4716. Min Act: -0.0001

Data Index: 1341606 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4664. Min Act: -0.0001

Data Index: 627617 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4385. Min Act: -0.0001

Data Index: 856634 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4276. Min Act: -0.0001

Data Index: 1068667 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4457. Min Act: -0.0001

Data Index: 1045651 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4096. Min Act: -0.0002

Data Index: 1288713 (C4 (Web Text))

Max Activating Token Index: 443

Text #8

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4065. Min Act: -0.0001

Data Index: 241263 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4284. Min Act: -0.0001

Data Index: 1110068 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4162. Min Act: -0.0001

Data Index: 218807 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4147. Min Act: -0.0001

Data Index: 922167 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4107. Min Act: -0.0002

Data Index: 457546 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4090. Min Act: -0.0001

Data Index: 1054860 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4235. Min Act: -0.0002

Data Index: 717736 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3813. Min Act: -0.0002

Data Index: 1204244 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4065. Min Act: -0.0001

Data Index: 1252950 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4285. Min Act: -0.0001

Data Index: 999220 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4066. Min Act: -0.0001

Data Index: 69728 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4027. Min Act: -0.0002

Data Index: 195418 (C4 (Web Text))

Max Activating Token Index: 464