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

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

Neuron 4061 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: 1.4007. Min Range: -1.4007

Max Act: 1.4007. Min Act: -0.0000

Data Index: 1479038 (Python Code)

Max Activating Token Index: 994

Text #1

Max Range: 1.4007. Min Range: -1.4007

Max Act: 1.2263. Min Act: -0.0000

Data Index: 1002899 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 1.4007. Min Range: -1.4007

Max Act: 1.2031. Min Act: -0.0000

Data Index: 838998 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 1.4007. Min Range: -1.4007

Max Act: 1.1349. Min Act: -0.0000

Data Index: 333060 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 1.4007. Min Range: -1.4007

Max Act: 1.0601. Min Act: -0.0000

Data Index: 1439355 (Python Code)

Max Activating Token Index: 999

Text #5

Max Range: 1.4007. Min Range: -1.4007

Max Act: 1.1655. Min Act: -0.0000

Data Index: 1155729 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 1.4007. Min Range: -1.4007

Max Act: 1.0936. Min Act: -0.0000

Data Index: 562291 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 1.4007. Min Range: -1.4007

Max Act: 1.0957. Min Act: -0.0000

Data Index: 216121 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 1.4007. Min Range: -1.4007

Max Act: 0.8826. Min Act: -0.0000

Data Index: 1498810 (Python Code)

Max Activating Token Index: 996

Text #9

Max Range: 1.4007. Min Range: -1.4007

Max Act: 1.0822. Min Act: -0.0000

Data Index: 1191763 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 1.4007. Min Range: -1.4007

Max Act: 1.0898. Min Act: -0.0000

Data Index: 1166207 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 1.4007. Min Range: -1.4007

Max Act: 1.0357. Min Act: -0.0000

Data Index: 511920 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 1.4007. Min Range: -1.4007

Max Act: 1.0154. Min Act: -0.0000

Data Index: 699695 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 1.4007. Min Range: -1.4007

Max Act: 1.0072. Min Act: -0.0000

Data Index: 28054 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 1.4007. Min Range: -1.4007

Max Act: 0.9846. Min Act: -0.0000

Data Index: 764490 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 1.4007. Min Range: -1.4007

Max Act: 0.9733. Min Act: -0.0000

Data Index: 882458 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 1.4007. Min Range: -1.4007

Max Act: 0.9904. Min Act: -0.0000

Data Index: 591036 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 1.4007. Min Range: -1.4007

Max Act: 1.0079. Min Act: -0.0000

Data Index: 154154 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 1.4007. Min Range: -1.4007

Max Act: 1.0023. Min Act: -0.0000

Data Index: 290300 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 1.4007. Min Range: -1.4007

Max Act: 0.9514. Min Act: -0.0000

Data Index: 57344 (C4 (Web Text))

Max Activating Token Index: 212