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

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

Neuron 3240 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.5437. Min Act: -0.0000

Data Index: 828911 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.3381. Min Act: -0.0001

Data Index: 992191 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.2364. Min Act: -0.0000

Data Index: 702094 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.2270. Min Act: -0.0000

Data Index: 1291090 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.2180. Min Act: -0.0001

Data Index: 825308 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.1453. Min Act: -0.0001

Data Index: 171365 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.1958. Min Act: -0.0001

Data Index: 1159329 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.1572. Min Act: -0.0001

Data Index: 274644 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.1763. Min Act: -0.0001

Data Index: 233099 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.0661. Min Act: -0.0001

Data Index: 755873 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.1133. Min Act: -0.0001

Data Index: 812458 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.1065. Min Act: -0.0001

Data Index: 195298 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.1069. Min Act: -0.0001

Data Index: 449064 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.0638. Min Act: -0.0001

Data Index: 582632 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.0512. Min Act: -0.0000

Data Index: 233218 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.0722. Min Act: -0.0000

Data Index: 894409 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.0389. Min Act: -0.0001

Data Index: 1038157 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.0348. Min Act: -0.0001

Data Index: 727122 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.1044. Min Act: -0.0001

Data Index: 968617 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.0291. Min Act: -0.0001

Data Index: 810348 (C4 (Web Text))

Max Activating Token Index: 19