Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2808 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9086. Min Range: -2.9086

Max Act: 2.8256. Min Act: -0.0000

Data Index: 142201 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 2.9086. Min Range: -2.9086

Max Act: 2.9086. Min Act: -0.0000

Data Index: 24792 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 2.9086. Min Range: -2.9086

Max Act: 2.4056. Min Act: -0.0000

Data Index: 904640 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 2.9086. Min Range: -2.9086

Max Act: 2.4775. Min Act: -0.0000

Data Index: 528958 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 2.9086. Min Range: -2.9086

Max Act: 2.7230. Min Act: -0.0000

Data Index: 1296915 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 2.9086. Min Range: -2.9086

Max Act: 2.4824. Min Act: -0.0000

Data Index: 200725 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 2.9086. Min Range: -2.9086

Max Act: 2.3031. Min Act: -0.0000

Data Index: 941547 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 2.9086. Min Range: -2.9086

Max Act: 2.5149. Min Act: -0.0000

Data Index: 485573 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 2.9086. Min Range: -2.9086

Max Act: 2.2423. Min Act: -0.0000

Data Index: 734638 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 2.9086. Min Range: -2.9086

Max Act: 2.2244. Min Act: -0.0000

Data Index: 64960 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 2.9086. Min Range: -2.9086

Max Act: 2.2232. Min Act: -0.0000

Data Index: 633437 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 2.9086. Min Range: -2.9086

Max Act: 2.1980. Min Act: -0.0000

Data Index: 442734 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 2.9086. Min Range: -2.9086

Max Act: 2.0766. Min Act: -0.0000

Data Index: 4249 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 2.9086. Min Range: -2.9086

Max Act: 1.9316. Min Act: -0.0000

Data Index: 1072325 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 2.9086. Min Range: -2.9086

Max Act: 2.1602. Min Act: -0.0000

Data Index: 184516 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 2.9086. Min Range: -2.9086

Max Act: 2.1155. Min Act: -0.0000

Data Index: 711781 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 2.9086. Min Range: -2.9086

Max Act: 2.1016. Min Act: -0.0000

Data Index: 293151 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 2.9086. Min Range: -2.9086

Max Act: 2.1248. Min Act: -0.0000

Data Index: 578297 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 2.9086. Min Range: -2.9086

Max Act: 2.0917. Min Act: -0.0000

Data Index: 748065 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 2.9086. Min Range: -2.9086

Max Act: 2.1110. Min Act: -0.0000

Data Index: 1327546 (C4 (Web Text))

Max Activating Token Index: 34