Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2645 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1939. Min Range: -1.1939

Max Act: 1.1939. Min Act: -0.0000

Data Index: 529672 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 1.1939. Min Range: -1.1939

Max Act: 1.1140. Min Act: -0.0000

Data Index: 1282632 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 1.1939. Min Range: -1.1939

Max Act: 1.1106. Min Act: -0.0000

Data Index: 753007 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 1.1939. Min Range: -1.1939

Max Act: 1.0754. Min Act: -0.0000

Data Index: 2815 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 1.1939. Min Range: -1.1939

Max Act: 1.0558. Min Act: -0.0000

Data Index: 97142 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 1.1939. Min Range: -1.1939

Max Act: 0.9949. Min Act: -0.0000

Data Index: 50413 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 1.1939. Min Range: -1.1939

Max Act: 0.9803. Min Act: -0.0000

Data Index: 1126937 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 1.1939. Min Range: -1.1939

Max Act: 0.9199. Min Act: -0.0000

Data Index: 1097886 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 1.1939. Min Range: -1.1939

Max Act: 0.9146. Min Act: -0.0000

Data Index: 105823 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 1.1939. Min Range: -1.1939

Max Act: 1.0328. Min Act: -0.0000

Data Index: 435996 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 1.1939. Min Range: -1.1939

Max Act: 0.9632. Min Act: -0.0000

Data Index: 708499 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 1.1939. Min Range: -1.1939

Max Act: 0.9498. Min Act: -0.0000

Data Index: 946454 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 1.1939. Min Range: -1.1939

Max Act: 0.9475. Min Act: -0.0000

Data Index: 495269 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 1.1939. Min Range: -1.1939

Max Act: 0.9556. Min Act: -0.0000

Data Index: 116646 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 1.1939. Min Range: -1.1939

Max Act: 1.0033. Min Act: -0.0000

Data Index: 97346 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 1.1939. Min Range: -1.1939

Max Act: 0.9337. Min Act: -0.0000

Data Index: 1246275 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 1.1939. Min Range: -1.1939

Max Act: 0.9221. Min Act: -0.0000

Data Index: 1598814 (Python Code)

Max Activating Token Index: 97

Text #17

Max Range: 1.1939. Min Range: -1.1939

Max Act: 0.9314. Min Act: -0.0000

Data Index: 1063389 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 1.1939. Min Range: -1.1939

Max Act: 0.9294. Min Act: -0.0000

Data Index: 828180 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 1.1939. Min Range: -1.1939

Max Act: 0.9167. Min Act: -0.0000

Data Index: 835400 (C4 (Web Text))

Max Activating Token Index: 627