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

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

Neuron 5301 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8046. Min Range: -0.8046

Max Act: 0.7890. Min Act: -0.0000

Data Index: 16271 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 0.8046. Min Range: -0.8046

Max Act: 0.8046. Min Act: -0.0000

Data Index: 1029549 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 0.8046. Min Range: -0.8046

Max Act: 0.6893. Min Act: -0.0000

Data Index: 338967 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 0.8046. Min Range: -0.8046

Max Act: 0.6760. Min Act: -0.0000

Data Index: 784321 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.8046. Min Range: -0.8046

Max Act: 0.6783. Min Act: -0.0000

Data Index: 1300068 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 0.8046. Min Range: -0.8046

Max Act: 0.6253. Min Act: -0.0000

Data Index: 1466126 (Python Code)

Max Activating Token Index: 846

Text #6

Max Range: 0.8046. Min Range: -0.8046

Max Act: 0.6327. Min Act: -0.0000

Data Index: 875597 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 0.8046. Min Range: -0.8046

Max Act: 0.5836. Min Act: -0.0000

Data Index: 108593 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 0.8046. Min Range: -0.8046

Max Act: 0.5838. Min Act: -0.0000

Data Index: 585943 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 0.8046. Min Range: -0.8046

Max Act: 0.5781. Min Act: -0.0000

Data Index: 895389 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 0.8046. Min Range: -0.8046

Max Act: 0.5916. Min Act: -0.0000

Data Index: 1597261 (Python Code)

Max Activating Token Index: 612

Text #11

Max Range: 0.8046. Min Range: -0.8046

Max Act: 0.5673. Min Act: -0.0000

Data Index: 1028479 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 0.8046. Min Range: -0.8046

Max Act: 0.5841. Min Act: -0.0000

Data Index: 1250337 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 0.8046. Min Range: -0.8046

Max Act: 0.5635. Min Act: -0.0000

Data Index: 1162931 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 0.8046. Min Range: -0.8046

Max Act: 0.5665. Min Act: -0.0000

Data Index: 828139 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 0.8046. Min Range: -0.8046

Max Act: 0.6089. Min Act: -0.0000

Data Index: 930664 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 0.8046. Min Range: -0.8046

Max Act: 0.5618. Min Act: -0.0000

Data Index: 1590563 (Python Code)

Max Activating Token Index: 106

Text #17

Max Range: 0.8046. Min Range: -0.8046

Max Act: 0.5498. Min Act: -0.0000

Data Index: 1387706 (Python Code)

Max Activating Token Index: 603

Text #18

Max Range: 0.8046. Min Range: -0.8046

Max Act: 0.5492. Min Act: -0.0000

Data Index: 128070 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 0.8046. Min Range: -0.8046

Max Act: 0.5647. Min Act: -0.0000

Data Index: 912994 (C4 (Web Text))

Max Activating Token Index: 157