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

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

Neuron 3220 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7469. Min Range: -1.7469

Max Act: 1.7041. Min Act: -0.0001

Data Index: 717128 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 1.7469. Min Range: -1.7469

Max Act: 1.7469. Min Act: -0.0001

Data Index: 1131577 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 1.7469. Min Range: -1.7469

Max Act: 1.6858. Min Act: -0.0001

Data Index: 476803 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 1.7469. Min Range: -1.7469

Max Act: 1.5280. Min Act: -0.0001

Data Index: 1084946 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 1.7469. Min Range: -1.7469

Max Act: 1.5239. Min Act: -0.0001

Data Index: 352396 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 1.7469. Min Range: -1.7469

Max Act: 1.5254. Min Act: -0.0001

Data Index: 984475 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 1.7469. Min Range: -1.7469

Max Act: 1.5129. Min Act: -0.0001

Data Index: 46737 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 1.7469. Min Range: -1.7469

Max Act: 1.4898. Min Act: -0.0001

Data Index: 818667 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 1.7469. Min Range: -1.7469

Max Act: 1.4968. Min Act: -0.0001

Data Index: 1016265 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 1.7469. Min Range: -1.7469

Max Act: 1.5265. Min Act: -0.0001

Data Index: 1133193 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 1.7469. Min Range: -1.7469

Max Act: 1.5204. Min Act: -0.0001

Data Index: 42204 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 1.7469. Min Range: -1.7469

Max Act: 1.4818. Min Act: -0.0001

Data Index: 603723 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 1.7469. Min Range: -1.7469

Max Act: 1.5235. Min Act: -0.0001

Data Index: 48206 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 1.7469. Min Range: -1.7469

Max Act: 1.5539. Min Act: -0.0001

Data Index: 658054 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 1.7469. Min Range: -1.7469

Max Act: 1.4531. Min Act: -0.0001

Data Index: 915939 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 1.7469. Min Range: -1.7469

Max Act: 1.4932. Min Act: -0.0001

Data Index: 1303175 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 1.7469. Min Range: -1.7469

Max Act: 1.4280. Min Act: -0.0001

Data Index: 432626 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 1.7469. Min Range: -1.7469

Max Act: 1.4766. Min Act: -0.0001

Data Index: 805982 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 1.7469. Min Range: -1.7469

Max Act: 1.4366. Min Act: -0.0001

Data Index: 841204 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 1.7469. Min Range: -1.7469

Max Act: 1.4826. Min Act: -0.0001

Data Index: 1296592 (C4 (Web Text))

Max Activating Token Index: 370