Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1978 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.4409. Min Act: -0.0001

Data Index: 1148160 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.4414. Min Act: -0.0001

Data Index: 49965 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.4111. Min Act: -0.0001

Data Index: 805506 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.4247. Min Act: -0.0001

Data Index: 587567 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.4274. Min Act: -0.0001

Data Index: 1107775 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.4224. Min Act: -0.0001

Data Index: 1113544 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.4511. Min Act: -0.0001

Data Index: 1358199 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.4299. Min Act: -0.0001

Data Index: 483388 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.4086. Min Act: -0.0001

Data Index: 212539 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3959. Min Act: -0.0001

Data Index: 1142730 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3946. Min Act: -0.0001

Data Index: 809854 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.4037. Min Act: -0.0001

Data Index: 1157169 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.4356. Min Act: -0.0001

Data Index: 1300752 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3956. Min Act: -0.0001

Data Index: 874582 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3988. Min Act: -0.0001

Data Index: 653482 (C4 (Web Text))

Max Activating Token Index: 41

Text #15

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3876. Min Act: -0.0001

Data Index: 99336 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3963. Min Act: -0.0001

Data Index: 1334877 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.4299. Min Act: -0.0001

Data Index: 1276427 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.4108. Min Act: -0.0001

Data Index: 675879 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3865. Min Act: -0.0001

Data Index: 487049 (C4 (Web Text))

Max Activating Token Index: 29