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

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

Neuron 1993 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.2971. Min Act: -0.0001

Data Index: 863470 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.2178. Min Act: -0.0001

Data Index: 283914 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.1808. Min Act: -0.0001

Data Index: 987454 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.2103. Min Act: -0.0001

Data Index: 598996 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.1818. Min Act: -0.0001

Data Index: 802307 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.1718. Min Act: -0.0001

Data Index: 1134805 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.2029. Min Act: -0.0001

Data Index: 940724 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.0531. Min Act: -0.0001

Data Index: 1461312 (Python Code)

Max Activating Token Index: 303

Text #8

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.1160. Min Act: -0.0001

Data Index: 765401 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.0372. Min Act: -0.0001

Data Index: 198109 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 1.2971. Min Range: -1.2971

Max Act: 0.9989. Min Act: -0.0001

Data Index: 1411338 (Python Code)

Max Activating Token Index: 792

Text #11

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.0280. Min Act: -0.0001

Data Index: 610212 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.0313. Min Act: -0.0001

Data Index: 167291 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 1.2971. Min Range: -1.2971

Max Act: 0.9096. Min Act: -0.0001

Data Index: 1169055 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.0292. Min Act: -0.0001

Data Index: 393137 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 1.2971. Min Range: -1.2971

Max Act: 0.8947. Min Act: -0.0001

Data Index: 154627 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.0178. Min Act: -0.0001

Data Index: 583838 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.0200. Min Act: -0.0001

Data Index: 1209956 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 1.2971. Min Range: -1.2971

Max Act: 0.8401. Min Act: -0.0001

Data Index: 1297735 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 1.2971. Min Range: -1.2971

Max Act: 0.9514. Min Act: -0.0001

Data Index: 1396278 (Python Code)

Max Activating Token Index: 569