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

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

Neuron 2962 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: 3.8988. Min Range: -3.8988

Max Act: 3.8988. Min Act: -0.0000

Data Index: 148694 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 3.8988. Min Range: -3.8988

Max Act: 3.6437. Min Act: -0.0000

Data Index: 324727 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 3.8988. Min Range: -3.8988

Max Act: 3.4988. Min Act: -0.0000

Data Index: 548502 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 3.8988. Min Range: -3.8988

Max Act: 3.0797. Min Act: -0.0000

Data Index: 902148 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 3.8988. Min Range: -3.8988

Max Act: 3.1818. Min Act: -0.0000

Data Index: 690771 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 3.8988. Min Range: -3.8988

Max Act: 3.2835. Min Act: -0.0000

Data Index: 1123729 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 3.8988. Min Range: -3.8988

Max Act: 3.0589. Min Act: -0.0000

Data Index: 1094533 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 3.8988. Min Range: -3.8988

Max Act: 2.9274. Min Act: -0.0000

Data Index: 792980 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 3.8988. Min Range: -3.8988

Max Act: 2.9885. Min Act: -0.0000

Data Index: 1020996 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 3.8988. Min Range: -3.8988

Max Act: 2.9490. Min Act: -0.0000

Data Index: 193985 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 3.8988. Min Range: -3.8988

Max Act: 2.9369. Min Act: -0.0000

Data Index: 759915 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 3.8988. Min Range: -3.8988

Max Act: 2.9288. Min Act: -0.0000

Data Index: 1096756 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 3.8988. Min Range: -3.8988

Max Act: 2.9173. Min Act: -0.0000

Data Index: 526505 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 3.8988. Min Range: -3.8988

Max Act: 2.9062. Min Act: -0.0000

Data Index: 387711 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 3.8988. Min Range: -3.8988

Max Act: 2.7503. Min Act: -0.0000

Data Index: 1354924 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 3.8988. Min Range: -3.8988

Max Act: 2.7886. Min Act: -0.0000

Data Index: 1030797 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 3.8988. Min Range: -3.8988

Max Act: 2.6150. Min Act: -0.0000

Data Index: 1249730 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 3.8988. Min Range: -3.8988

Max Act: 2.7432. Min Act: -0.0000

Data Index: 479101 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 3.8988. Min Range: -3.8988

Max Act: 2.7274. Min Act: -0.0000

Data Index: 853723 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 3.8988. Min Range: -3.8988

Max Act: 2.6581. Min Act: -0.0000

Data Index: 956683 (C4 (Web Text))

Max Activating Token Index: 50