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

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

Neuron 6007 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.6967. Min Act: -0.0000

Data Index: 206282 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.6734. Min Act: -0.0000

Data Index: 928557 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.6263. Min Act: -0.0000

Data Index: 820354 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5890. Min Act: -0.0000

Data Index: 364046 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5882. Min Act: -0.0000

Data Index: 550680 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.6215. Min Act: -0.0000

Data Index: 363837 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.6109. Min Act: -0.0000

Data Index: 688837 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.6131. Min Act: -0.0000

Data Index: 847205 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5483. Min Act: -0.0000

Data Index: 981898 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5456. Min Act: -0.0000

Data Index: 28781 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5782. Min Act: -0.0000

Data Index: 1232651 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5232. Min Act: -0.0000

Data Index: 1169726 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5565. Min Act: -0.0000

Data Index: 832911 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.6105. Min Act: -0.0000

Data Index: 1095848 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5518. Min Act: -0.0000

Data Index: 191913 (C4 (Web Text))

Max Activating Token Index: 245

Text #15

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5381. Min Act: -0.0000

Data Index: 425329 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5384. Min Act: -0.0000

Data Index: 1315220 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5198. Min Act: -0.0000

Data Index: 1187038 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5340. Min Act: -0.0000

Data Index: 711406 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5106. Min Act: -0.0000

Data Index: 1478257 (Python Code)

Max Activating Token Index: 222