Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2047 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.1037. Min Range: -5.1037

Max Act: 5.1037. Min Act: -0.0001

Data Index: 275444 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 5.1037. Min Range: -5.1037

Max Act: 4.6627. Min Act: -0.0001

Data Index: 1169886 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 5.1037. Min Range: -5.1037

Max Act: 4.5059. Min Act: -0.0001

Data Index: 904402 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 5.1037. Min Range: -5.1037

Max Act: 4.5086. Min Act: -0.0001

Data Index: 1177789 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 5.1037. Min Range: -5.1037

Max Act: 4.3222. Min Act: -0.0001

Data Index: 879301 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 5.1037. Min Range: -5.1037

Max Act: 4.1764. Min Act: -0.0001

Data Index: 1337827 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 5.1037. Min Range: -5.1037

Max Act: 3.9788. Min Act: -0.0001

Data Index: 746552 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 5.1037. Min Range: -5.1037

Max Act: 3.9895. Min Act: -0.0001

Data Index: 1349507 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 5.1037. Min Range: -5.1037

Max Act: 3.9560. Min Act: -0.0001

Data Index: 121452 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 5.1037. Min Range: -5.1037

Max Act: 3.9464. Min Act: -0.0001

Data Index: 913247 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 5.1037. Min Range: -5.1037

Max Act: 3.6016. Min Act: -0.0001

Data Index: 1119219 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 5.1037. Min Range: -5.1037

Max Act: 3.8155. Min Act: -0.0001

Data Index: 1346130 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 5.1037. Min Range: -5.1037

Max Act: 3.9288. Min Act: -0.0001

Data Index: 546316 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 5.1037. Min Range: -5.1037

Max Act: 3.6079. Min Act: -0.0001

Data Index: 129558 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 5.1037. Min Range: -5.1037

Max Act: 3.9199. Min Act: -0.0001

Data Index: 868247 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 5.1037. Min Range: -5.1037

Max Act: 3.6202. Min Act: -0.0001

Data Index: 384962 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 5.1037. Min Range: -5.1037

Max Act: 3.7389. Min Act: -0.0001

Data Index: 1002505 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 5.1037. Min Range: -5.1037

Max Act: 3.6713. Min Act: -0.0001

Data Index: 510237 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 5.1037. Min Range: -5.1037

Max Act: 3.6814. Min Act: -0.0001

Data Index: 399663 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 5.1037. Min Range: -5.1037

Max Act: 3.6439. Min Act: -0.0001

Data Index: 125821 (C4 (Web Text))

Max Activating Token Index: 126