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

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

Neuron 5572 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.7888. Min Act: -0.0000

Data Index: 646933 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.5707. Min Act: -0.0000

Data Index: 592511 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.6059. Min Act: -0.0000

Data Index: 397412 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.5412. Min Act: -0.0000

Data Index: 218343 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.5494. Min Act: -0.0000

Data Index: 1198161 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.4306. Min Act: -0.0000

Data Index: 1188261 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.4948. Min Act: -0.0000

Data Index: 472435 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.5833. Min Act: -0.0000

Data Index: 802127 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.4932. Min Act: -0.0000

Data Index: 1313882 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.4962. Min Act: -0.0000

Data Index: 828153 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.4804. Min Act: -0.0000

Data Index: 994386 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.2917. Min Act: -0.0000

Data Index: 812613 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.3637. Min Act: -0.0000

Data Index: 1576066 (Python Code)

Max Activating Token Index: 1002

Text #13

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.3286. Min Act: -0.0000

Data Index: 1329384 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.4051. Min Act: -0.0000

Data Index: 622926 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.4815. Min Act: -0.0000

Data Index: 220179 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.3820. Min Act: -0.0000

Data Index: 756669 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.3739. Min Act: -0.0000

Data Index: 136080 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.2934. Min Act: -0.0000

Data Index: 387759 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.2907. Min Act: -0.0000

Data Index: 629688 (C4 (Web Text))

Max Activating Token Index: 975