Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1732 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0306. Min Range: -1.0306

Max Act: 1.0210. Min Act: -0.0001

Data Index: 1105085 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.9695. Min Act: -0.0001

Data Index: 161790 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 1.0306. Min Range: -1.0306

Max Act: 1.0306. Min Act: -0.0001

Data Index: 547070 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8550. Min Act: -0.0001

Data Index: 767776 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.9316. Min Act: -0.0001

Data Index: 986783 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.9109. Min Act: -0.0001

Data Index: 445550 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8952. Min Act: -0.0001

Data Index: 622592 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8813. Min Act: -0.0001

Data Index: 684283 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8919. Min Act: -0.0001

Data Index: 1043909 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8527. Min Act: -0.0001

Data Index: 912594 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8121. Min Act: -0.0001

Data Index: 1250039 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8314. Min Act: -0.0001

Data Index: 743140 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8521. Min Act: -0.0001

Data Index: 358580 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8283. Min Act: -0.0001

Data Index: 1116671 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7956. Min Act: -0.0001

Data Index: 272138 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8171. Min Act: -0.0001

Data Index: 22705 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8138. Min Act: -0.0001

Data Index: 243675 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7983. Min Act: -0.0001

Data Index: 855956 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7431. Min Act: -0.0001

Data Index: 1012324 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8103. Min Act: -0.0001

Data Index: 856066 (C4 (Web Text))

Max Activating Token Index: 297