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

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

Neuron 1003 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1965. Min Range: -2.1965

Max Act: 2.1965. Min Act: -0.0000

Data Index: 352468 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 2.1965. Min Range: -2.1965

Max Act: 2.1761. Min Act: -0.0000

Data Index: 794292 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 2.1965. Min Range: -2.1965

Max Act: 1.9223. Min Act: -0.0000

Data Index: 635478 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 2.1965. Min Range: -2.1965

Max Act: 2.0199. Min Act: -0.0000

Data Index: 1012292 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 2.1965. Min Range: -2.1965

Max Act: 1.9010. Min Act: -0.0000

Data Index: 1342091 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 2.1965. Min Range: -2.1965

Max Act: 1.8196. Min Act: -0.0000

Data Index: 758287 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 2.1965. Min Range: -2.1965

Max Act: 1.6128. Min Act: -0.0000

Data Index: 305354 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 2.1965. Min Range: -2.1965

Max Act: 1.8894. Min Act: -0.0000

Data Index: 25656 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 2.1965. Min Range: -2.1965

Max Act: 1.7539. Min Act: -0.0000

Data Index: 885801 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 2.1965. Min Range: -2.1965

Max Act: 1.6609. Min Act: -0.0000

Data Index: 1072881 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 2.1965. Min Range: -2.1965

Max Act: 1.7332. Min Act: -0.0000

Data Index: 194970 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 2.1965. Min Range: -2.1965

Max Act: 1.5983. Min Act: -0.0000

Data Index: 842720 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 2.1965. Min Range: -2.1965

Max Act: 1.6612. Min Act: -0.0000

Data Index: 1019934 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 2.1965. Min Range: -2.1965

Max Act: 1.6716. Min Act: -0.0000

Data Index: 668501 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 2.1965. Min Range: -2.1965

Max Act: 1.6623. Min Act: -0.0000

Data Index: 1280784 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 2.1965. Min Range: -2.1965

Max Act: 1.6485. Min Act: -0.0000

Data Index: 1044232 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 2.1965. Min Range: -2.1965

Max Act: 1.5585. Min Act: -0.0000

Data Index: 210051 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 2.1965. Min Range: -2.1965

Max Act: 1.6408. Min Act: -0.0000

Data Index: 834483 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 2.1965. Min Range: -2.1965

Max Act: 1.6211. Min Act: -0.0000

Data Index: 313912 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 2.1965. Min Range: -2.1965

Max Act: 1.5298. Min Act: -0.0000

Data Index: 1208820 (C4 (Web Text))

Max Activating Token Index: 205