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

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

Neuron 373 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: 3.7750. Min Range: -3.7750

Max Act: 3.7750. Min Act: -0.0001

Data Index: 1308567 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.0684. Min Act: -0.0001

Data Index: 1083024 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.0359. Min Act: -0.0001

Data Index: 598529 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 3.7750. Min Range: -3.7750

Max Act: 2.9618. Min Act: -0.0001

Data Index: 18493 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.1462. Min Act: -0.0001

Data Index: 468450 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 3.7750. Min Range: -3.7750

Max Act: 2.8449. Min Act: -0.0000

Data Index: 1107155 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 3.7750. Min Range: -3.7750

Max Act: 2.8008. Min Act: -0.0000

Data Index: 38224 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 3.7750. Min Range: -3.7750

Max Act: 2.9190. Min Act: -0.0000

Data Index: 683120 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 3.7750. Min Range: -3.7750

Max Act: 2.7566. Min Act: -0.0000

Data Index: 679562 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 3.7750. Min Range: -3.7750

Max Act: 2.6283. Min Act: -0.0001

Data Index: 461273 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 3.7750. Min Range: -3.7750

Max Act: 2.7450. Min Act: -0.0000

Data Index: 1207060 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 3.7750. Min Range: -3.7750

Max Act: 2.7154. Min Act: -0.0001

Data Index: 45175 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 3.7750. Min Range: -3.7750

Max Act: 2.5712. Min Act: -0.0000

Data Index: 1208066 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 3.7750. Min Range: -3.7750

Max Act: 2.6217. Min Act: -0.0001

Data Index: 514341 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 3.7750. Min Range: -3.7750

Max Act: 2.5874. Min Act: -0.0000

Data Index: 772568 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 3.7750. Min Range: -3.7750

Max Act: 2.4210. Min Act: -0.0001

Data Index: 519439 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 3.7750. Min Range: -3.7750

Max Act: 2.5527. Min Act: -0.0001

Data Index: 347756 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 3.7750. Min Range: -3.7750

Max Act: 2.5090. Min Act: -0.0000

Data Index: 685274 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 3.7750. Min Range: -3.7750

Max Act: 2.4993. Min Act: -0.0000

Data Index: 998077 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 3.7750. Min Range: -3.7750

Max Act: 2.4850. Min Act: -0.0000

Data Index: 853939 (C4 (Web Text))

Max Activating Token Index: 383