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

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

Neuron 1047 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: 0.3179. Min Range: -0.3179

Max Act: 0.3179. Min Act: -0.0000

Data Index: 1632070 (Python Code)

Max Activating Token Index: 924

Text #1

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.1140. Min Act: -0.0000

Data Index: 1455502 (Python Code)

Max Activating Token Index: 1013

Text #2

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.0580. Min Act: -0.0000

Data Index: 1370110 (Python Code)

Max Activating Token Index: 998

Text #3

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.0464. Min Act: -0.0000

Data Index: 1076712 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.0412. Min Act: -0.0000

Data Index: 1202416 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.0405. Min Act: -0.0001

Data Index: 29371 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.0373. Min Act: -0.0001

Data Index: 1345857 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.0387. Min Act: -0.0000

Data Index: 1457712 (Python Code)

Max Activating Token Index: 1008

Text #8

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.0366. Min Act: -0.0001

Data Index: 793231 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.0371. Min Act: -0.0000

Data Index: 1623036 (Python Code)

Max Activating Token Index: 1006

Text #10

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.0361. Min Act: -0.0001

Data Index: 1377361 (Python Code)

Max Activating Token Index: 995

Text #11

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.0352. Min Act: -0.0001

Data Index: 594996 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.0290. Min Act: -0.0001

Data Index: 1398357 (Python Code)

Max Activating Token Index: 954

Text #13

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.0334. Min Act: -0.0000

Data Index: 909330 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.0336. Min Act: -0.0001

Data Index: 20756 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.0351. Min Act: -0.0001

Data Index: 287984 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.0314. Min Act: -0.0000

Data Index: 194202 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.0320. Min Act: -0.0001

Data Index: 1120473 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.0309. Min Act: -0.0000

Data Index: 1416156 (Python Code)

Max Activating Token Index: 997

Text #19

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.0319. Min Act: -0.0001

Data Index: 629723 (C4 (Web Text))

Max Activating Token Index: 1009