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

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

Neuron 104 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1045. Min Range: -7.1045

Max Act: 7.1045. Min Act: -0.0000

Data Index: 823009 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 7.1045. Min Range: -7.1045

Max Act: 6.4440. Min Act: -0.0000

Data Index: 1350297 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 7.1045. Min Range: -7.1045

Max Act: 5.6636. Min Act: -0.0000

Data Index: 626078 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 7.1045. Min Range: -7.1045

Max Act: 5.6627. Min Act: -0.0000

Data Index: 1255190 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 7.1045. Min Range: -7.1045

Max Act: 5.7916. Min Act: -0.0000

Data Index: 774445 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 7.1045. Min Range: -7.1045

Max Act: 5.5147. Min Act: -0.0000

Data Index: 405278 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 7.1045. Min Range: -7.1045

Max Act: 5.1799. Min Act: -0.0000

Data Index: 378209 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 7.1045. Min Range: -7.1045

Max Act: 5.0021. Min Act: -0.0000

Data Index: 323119 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 7.1045. Min Range: -7.1045

Max Act: 5.1522. Min Act: -0.0000

Data Index: 478380 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 7.1045. Min Range: -7.1045

Max Act: 4.9138. Min Act: -0.0000

Data Index: 1196271 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 7.1045. Min Range: -7.1045

Max Act: 5.2703. Min Act: -0.0000

Data Index: 1015199 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 7.1045. Min Range: -7.1045

Max Act: 5.2409. Min Act: -0.0000

Data Index: 709945 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 7.1045. Min Range: -7.1045

Max Act: 5.2018. Min Act: -0.0000

Data Index: 865705 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 7.1045. Min Range: -7.1045

Max Act: 5.3734. Min Act: -0.0000

Data Index: 890411 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 7.1045. Min Range: -7.1045

Max Act: 5.3252. Min Act: -0.0000

Data Index: 1199925 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 7.1045. Min Range: -7.1045

Max Act: 5.0715. Min Act: -0.0000

Data Index: 1054695 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 7.1045. Min Range: -7.1045

Max Act: 5.2450. Min Act: -0.0000

Data Index: 392085 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 7.1045. Min Range: -7.1045

Max Act: 5.0166. Min Act: -0.0000

Data Index: 326826 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 7.1045. Min Range: -7.1045

Max Act: 4.8471. Min Act: -0.0000

Data Index: 1356101 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 7.1045. Min Range: -7.1045

Max Act: 5.0097. Min Act: -0.0000

Data Index: 1073896 (C4 (Web Text))

Max Activating Token Index: 682