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

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

Neuron 1699 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1570. Min Range: -3.1570

Max Act: 3.0521. Min Act: -0.0000

Data Index: 509478 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 3.1570. Min Range: -3.1570

Max Act: 3.1570. Min Act: -0.0000

Data Index: 268715 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 3.1570. Min Range: -3.1570

Max Act: 2.6786. Min Act: -0.0000

Data Index: 596994 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 3.1570. Min Range: -3.1570

Max Act: 2.3602. Min Act: -0.0000

Data Index: 617510 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 3.1570. Min Range: -3.1570

Max Act: 2.4051. Min Act: -0.0000

Data Index: 1271121 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 3.1570. Min Range: -3.1570

Max Act: 2.5154. Min Act: -0.0000

Data Index: 1275720 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 3.1570. Min Range: -3.1570

Max Act: 2.5241. Min Act: -0.0000

Data Index: 334761 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 3.1570. Min Range: -3.1570

Max Act: 2.3034. Min Act: -0.0000

Data Index: 1311064 (C4 (Web Text))

Max Activating Token Index: 345

Text #8

Max Range: 3.1570. Min Range: -3.1570

Max Act: 2.2199. Min Act: -0.0000

Data Index: 1172732 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 3.1570. Min Range: -3.1570

Max Act: 2.3332. Min Act: -0.0000

Data Index: 1044610 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 3.1570. Min Range: -3.1570

Max Act: 2.3131. Min Act: -0.0000

Data Index: 1208427 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 3.1570. Min Range: -3.1570

Max Act: 2.1406. Min Act: -0.0000

Data Index: 649301 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 3.1570. Min Range: -3.1570

Max Act: 2.2560. Min Act: -0.0000

Data Index: 1151357 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 3.1570. Min Range: -3.1570

Max Act: 2.0309. Min Act: -0.0000

Data Index: 1266628 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 3.1570. Min Range: -3.1570

Max Act: 2.2136. Min Act: -0.0000

Data Index: 403230 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.1570. Min Range: -3.1570

Max Act: 2.2972. Min Act: -0.0000

Data Index: 106047 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 3.1570. Min Range: -3.1570

Max Act: 2.2383. Min Act: -0.0000

Data Index: 163627 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 3.1570. Min Range: -3.1570

Max Act: 2.0007. Min Act: -0.0000

Data Index: 754467 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 3.1570. Min Range: -3.1570

Max Act: 1.9878. Min Act: -0.0000

Data Index: 473911 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 3.1570. Min Range: -3.1570

Max Act: 2.3365. Min Act: -0.0000

Data Index: 384500 (C4 (Web Text))

Max Activating Token Index: 791