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

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

Neuron 303 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2592. Min Act: -0.0000

Data Index: 38070 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2503. Min Act: 0.0000

Data Index: 438455 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2480. Min Act: -0.0000

Data Index: 185465 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2363. Min Act: -0.0000

Data Index: 438396 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2180. Min Act: -0.0000

Data Index: 1244479 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2242. Min Act: -0.0000

Data Index: 778762 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2243. Min Act: 0.0000

Data Index: 640169 (C4 (Web Text))

Max Activating Token Index: 321

Text #7

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2231. Min Act: -0.0000

Data Index: 544605 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2286. Min Act: -0.0000

Data Index: 1319464 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2188. Min Act: 0.0001

Data Index: 464440 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2081. Min Act: -0.0000

Data Index: 19990 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2033. Min Act: -0.0000

Data Index: 391022 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1944. Min Act: 0.0000

Data Index: 1197947 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1988. Min Act: -0.0000

Data Index: 420925 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1904. Min Act: -0.0001

Data Index: 702524 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1985. Min Act: -0.0000

Data Index: 993856 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1908. Min Act: -0.0000

Data Index: 684207 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2022. Min Act: -0.0001

Data Index: 1324678 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1946. Min Act: -0.0000

Data Index: 847418 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1867. Min Act: -0.0001

Data Index: 266664 (C4 (Web Text))

Max Activating Token Index: 793