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

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

Neuron 1397 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.3065. Min Act: -0.0001

Data Index: 255722 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.2700. Min Act: -0.0001

Data Index: 14430 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.1364. Min Act: -0.0001

Data Index: 501063 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.1207. Min Act: -0.0001

Data Index: 604457 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.1331. Min Act: -0.0001

Data Index: 33560 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.0846. Min Act: -0.0001

Data Index: 148098 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.0395. Min Act: -0.0001

Data Index: 309616 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 1.3065. Min Range: -1.3065

Max Act: 0.9679. Min Act: -0.0001

Data Index: 488130 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.0591. Min Act: -0.0001

Data Index: 1076021 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 1.3065. Min Range: -1.3065

Max Act: 0.9605. Min Act: -0.0001

Data Index: 533198 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.0013. Min Act: -0.0001

Data Index: 696893 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.0364. Min Act: -0.0001

Data Index: 1061063 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 1.3065. Min Range: -1.3065

Max Act: 0.9570. Min Act: -0.0001

Data Index: 710270 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 1.3065. Min Range: -1.3065

Max Act: 0.9648. Min Act: -0.0001

Data Index: 576874 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 1.3065. Min Range: -1.3065

Max Act: 0.9403. Min Act: -0.0001

Data Index: 614236 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 1.3065. Min Range: -1.3065

Max Act: 0.9916. Min Act: -0.0001

Data Index: 299983 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 1.3065. Min Range: -1.3065

Max Act: 0.9574. Min Act: -0.0001

Data Index: 157583 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 1.3065. Min Range: -1.3065

Max Act: 0.9601. Min Act: -0.0001

Data Index: 521850 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.0163. Min Act: -0.0001

Data Index: 1000818 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 1.3065. Min Range: -1.3065

Max Act: 0.9801. Min Act: -0.0001

Data Index: 79516 (C4 (Web Text))

Max Activating Token Index: 216