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

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

Neuron 4835 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0211. Min Range: -1.0211

Max Act: 1.0211. Min Act: -0.0000

Data Index: 264047 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.8865. Min Act: -0.0000

Data Index: 718314 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 1.0211. Min Range: -1.0211

Max Act: 1.0016. Min Act: -0.0000

Data Index: 216797 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.9099. Min Act: -0.0000

Data Index: 988220 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.9734. Min Act: -0.0000

Data Index: 800131 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.8924. Min Act: -0.0000

Data Index: 566322 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.8185. Min Act: -0.0000

Data Index: 1400434 (Python Code)

Max Activating Token Index: 142

Text #7

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.8757. Min Act: -0.0000

Data Index: 1539327 (Python Code)

Max Activating Token Index: 69

Text #8

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.8802. Min Act: -0.0000

Data Index: 420832 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.9011. Min Act: -0.0000

Data Index: 1117575 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.8137. Min Act: -0.0000

Data Index: 594616 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.8307. Min Act: -0.0000

Data Index: 4039 (C4 (Web Text))

Max Activating Token Index: 464

Text #12

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.8671. Min Act: -0.0000

Data Index: 977006 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.8276. Min Act: -0.0000

Data Index: 521478 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.8245. Min Act: -0.0000

Data Index: 418140 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.8777. Min Act: -0.0000

Data Index: 571378 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.8431. Min Act: -0.0000

Data Index: 397234 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.8877. Min Act: -0.0000

Data Index: 782460 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.8144. Min Act: -0.0000

Data Index: 292528 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 1.0211. Min Range: -1.0211

Max Act: 0.7933. Min Act: -0.0000

Data Index: 441429 (C4 (Web Text))

Max Activating Token Index: 914