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

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

Neuron 4386 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0534. Min Range: -2.0534

Max Act: 2.0534. Min Act: -0.0000

Data Index: 359847 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 2.0534. Min Range: -2.0534

Max Act: 1.6946. Min Act: -0.0000

Data Index: 516605 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 2.0534. Min Range: -2.0534

Max Act: 1.8631. Min Act: -0.0000

Data Index: 811733 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 2.0534. Min Range: -2.0534

Max Act: 1.6872. Min Act: -0.0000

Data Index: 478729 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 2.0534. Min Range: -2.0534

Max Act: 1.6110. Min Act: -0.0000

Data Index: 1271557 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 2.0534. Min Range: -2.0534

Max Act: 1.6461. Min Act: -0.0000

Data Index: 1033026 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 2.0534. Min Range: -2.0534

Max Act: 1.6192. Min Act: -0.0000

Data Index: 835490 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 2.0534. Min Range: -2.0534

Max Act: 1.5107. Min Act: -0.0000

Data Index: 914765 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 2.0534. Min Range: -2.0534

Max Act: 1.5509. Min Act: -0.0000

Data Index: 760935 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 2.0534. Min Range: -2.0534

Max Act: 1.4060. Min Act: -0.0000

Data Index: 1051613 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 2.0534. Min Range: -2.0534

Max Act: 1.3379. Min Act: -0.0000

Data Index: 149970 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 2.0534. Min Range: -2.0534

Max Act: 1.3172. Min Act: -0.0000

Data Index: 464022 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 2.0534. Min Range: -2.0534

Max Act: 1.3512. Min Act: -0.0000

Data Index: 1122218 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 2.0534. Min Range: -2.0534

Max Act: 1.2914. Min Act: -0.0000

Data Index: 1187585 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 2.0534. Min Range: -2.0534

Max Act: 1.3189. Min Act: -0.0000

Data Index: 1129814 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 2.0534. Min Range: -2.0534

Max Act: 1.3546. Min Act: -0.0000

Data Index: 950415 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 2.0534. Min Range: -2.0534

Max Act: 1.2176. Min Act: -0.0000

Data Index: 993493 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 2.0534. Min Range: -2.0534

Max Act: 1.2840. Min Act: -0.0000

Data Index: 811111 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 2.0534. Min Range: -2.0534

Max Act: 1.3727. Min Act: -0.0000

Data Index: 274357 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 2.0534. Min Range: -2.0534

Max Act: 1.2976. Min Act: -0.0000

Data Index: 173756 (C4 (Web Text))

Max Activating Token Index: 849