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

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

Neuron 1529 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.9090. Min Act: -0.0000

Data Index: 1650275 (Python Code)

Max Activating Token Index: 157

Text #1

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.8500. Min Act: -0.0000

Data Index: 41552 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.7072. Min Act: -0.0001

Data Index: 1599001 (Python Code)

Max Activating Token Index: 916

Text #3

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.7069. Min Act: -0.0001

Data Index: 1633139 (Python Code)

Max Activating Token Index: 908

Text #4

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.5973. Min Act: -0.0000

Data Index: 1601748 (Python Code)

Max Activating Token Index: 224

Text #5

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.6841. Min Act: -0.0000

Data Index: 1371304 (Python Code)

Max Activating Token Index: 873

Text #6

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.6888. Min Act: -0.0000

Data Index: 1603690 (Python Code)

Max Activating Token Index: 95

Text #7

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.5117. Min Act: -0.0000

Data Index: 1366827 (Python Code)

Max Activating Token Index: 464

Text #8

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.6069. Min Act: -0.0000

Data Index: 400192 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.6413. Min Act: -0.0001

Data Index: 1480365 (Python Code)

Max Activating Token Index: 757

Text #10

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.5903. Min Act: -0.0000

Data Index: 1436767 (Python Code)

Max Activating Token Index: 673

Text #11

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.6202. Min Act: -0.0000

Data Index: 974263 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.5734. Min Act: -0.0000

Data Index: 160809 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.5657. Min Act: -0.0000

Data Index: 1260194 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.6174. Min Act: -0.0000

Data Index: 1540718 (Python Code)

Max Activating Token Index: 750

Text #15

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.5538. Min Act: -0.0000

Data Index: 1386429 (Python Code)

Max Activating Token Index: 950

Text #16

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.5383. Min Act: -0.0000

Data Index: 1467182 (Python Code)

Max Activating Token Index: 585

Text #17

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.5209. Min Act: -0.0000

Data Index: 1253833 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.5470. Min Act: -0.0000

Data Index: 1179194 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.5079. Min Act: -0.0001

Data Index: 1370352 (Python Code)

Max Activating Token Index: 673