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

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

Neuron 5490 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: 5.0968. Min Range: -5.0968

Max Act: 5.0968. Min Act: -0.0000

Data Index: 684623 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 5.0968. Min Range: -5.0968

Max Act: 4.4635. Min Act: -0.0000

Data Index: 175768 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 5.0968. Min Range: -5.0968

Max Act: 3.8413. Min Act: -0.0000

Data Index: 101946 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 5.0968. Min Range: -5.0968

Max Act: 3.9184. Min Act: -0.0000

Data Index: 1027911 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 5.0968. Min Range: -5.0968

Max Act: 3.9038. Min Act: -0.0000

Data Index: 575319 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 5.0968. Min Range: -5.0968

Max Act: 3.8628. Min Act: -0.0000

Data Index: 1337794 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 5.0968. Min Range: -5.0968

Max Act: 3.7181. Min Act: -0.0000

Data Index: 532838 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 5.0968. Min Range: -5.0968

Max Act: 3.1980. Min Act: -0.0000

Data Index: 186678 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 5.0968. Min Range: -5.0968

Max Act: 3.6507. Min Act: -0.0000

Data Index: 937908 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 5.0968. Min Range: -5.0968

Max Act: 3.6085. Min Act: -0.0000

Data Index: 643436 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 5.0968. Min Range: -5.0968

Max Act: 3.3769. Min Act: -0.0000

Data Index: 36844 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 5.0968. Min Range: -5.0968

Max Act: 3.4582. Min Act: -0.0000

Data Index: 1093022 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 5.0968. Min Range: -5.0968

Max Act: 3.3091. Min Act: -0.0000

Data Index: 745920 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 5.0968. Min Range: -5.0968

Max Act: 3.4464. Min Act: -0.0000

Data Index: 685989 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 5.0968. Min Range: -5.0968

Max Act: 3.5677. Min Act: -0.0000

Data Index: 737510 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 5.0968. Min Range: -5.0968

Max Act: 3.4251. Min Act: -0.0000

Data Index: 516222 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 5.0968. Min Range: -5.0968

Max Act: 3.5749. Min Act: -0.0000

Data Index: 965810 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 5.0968. Min Range: -5.0968

Max Act: 3.2611. Min Act: -0.0000

Data Index: 1102866 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 5.0968. Min Range: -5.0968

Max Act: 3.2187. Min Act: -0.0000

Data Index: 128215 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 5.0968. Min Range: -5.0968

Max Act: 3.1884. Min Act: -0.0000

Data Index: 1259510 (C4 (Web Text))

Max Activating Token Index: 846