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

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

Neuron 3456 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: 0.2766. Min Range: -0.2766

Max Act: 0.2766. Min Act: -0.0000

Data Index: 1058242 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2424. Min Act: -0.0000

Data Index: 652999 (C4 (Web Text))

Max Activating Token Index: 478

Text #2

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2243. Min Act: -0.0000

Data Index: 995524 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2331. Min Act: -0.0001

Data Index: 83468 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2147. Min Act: -0.0001

Data Index: 402373 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2104. Min Act: -0.0000

Data Index: 294291 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2093. Min Act: -0.0000

Data Index: 1254205 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2104. Min Act: -0.0000

Data Index: 1307184 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2029. Min Act: -0.0000

Data Index: 343041 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2083. Min Act: -0.0001

Data Index: 1310161 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1998. Min Act: -0.0001

Data Index: 510966 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2052. Min Act: -0.0000

Data Index: 933305 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1940. Min Act: -0.0000

Data Index: 344042 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1973. Min Act: -0.0001

Data Index: 633789 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1921. Min Act: -0.0000

Data Index: 669839 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2041. Min Act: -0.0001

Data Index: 1156056 (C4 (Web Text))

Max Activating Token Index: 459

Text #16

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1957. Min Act: -0.0001

Data Index: 916726 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1950. Min Act: -0.0000

Data Index: 560568 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2016. Min Act: -0.0001

Data Index: 693526 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1938. Min Act: -0.0001

Data Index: 775153 (C4 (Web Text))

Max Activating Token Index: 665