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

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

Neuron 310 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: 1.0059. Min Range: -1.0059

Max Act: 1.0059. Min Act: -0.0000

Data Index: 381590 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 1.0059. Min Range: -1.0059

Max Act: 0.9330. Min Act: -0.0000

Data Index: 1042448 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 1.0059. Min Range: -1.0059

Max Act: 0.9006. Min Act: -0.0000

Data Index: 209981 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 1.0059. Min Range: -1.0059

Max Act: 0.9204. Min Act: -0.0000

Data Index: 213986 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 1.0059. Min Range: -1.0059

Max Act: 0.8465. Min Act: -0.0000

Data Index: 588252 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 1.0059. Min Range: -1.0059

Max Act: 0.8974. Min Act: -0.0000

Data Index: 319003 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 1.0059. Min Range: -1.0059

Max Act: 0.8828. Min Act: -0.0000

Data Index: 1102038 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 1.0059. Min Range: -1.0059

Max Act: 0.8830. Min Act: -0.0000

Data Index: 22491 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 1.0059. Min Range: -1.0059

Max Act: 0.8784. Min Act: -0.0000

Data Index: 652499 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 1.0059. Min Range: -1.0059

Max Act: 0.8433. Min Act: -0.0000

Data Index: 1256381 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 1.0059. Min Range: -1.0059

Max Act: 0.8088. Min Act: -0.0000

Data Index: 1321640 (C4 (Web Text))

Max Activating Token Index: 412

Text #11

Max Range: 1.0059. Min Range: -1.0059

Max Act: 0.8626. Min Act: -0.0000

Data Index: 360090 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 1.0059. Min Range: -1.0059

Max Act: 0.8353. Min Act: -0.0000

Data Index: 938435 (C4 (Web Text))

Max Activating Token Index: 740

Text #13

Max Range: 1.0059. Min Range: -1.0059

Max Act: 0.8066. Min Act: -0.0000

Data Index: 1170956 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 1.0059. Min Range: -1.0059

Max Act: 0.7807. Min Act: -0.0000

Data Index: 395047 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 1.0059. Min Range: -1.0059

Max Act: 0.8259. Min Act: -0.0000

Data Index: 218270 (C4 (Web Text))

Max Activating Token Index: 478

Text #16

Max Range: 1.0059. Min Range: -1.0059

Max Act: 0.7975. Min Act: -0.0000

Data Index: 912039 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 1.0059. Min Range: -1.0059

Max Act: 0.8067. Min Act: -0.0000

Data Index: 1159347 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 1.0059. Min Range: -1.0059

Max Act: 0.8381. Min Act: -0.0000

Data Index: 642934 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 1.0059. Min Range: -1.0059

Max Act: 0.8634. Min Act: -0.0000

Data Index: 898842 (C4 (Web Text))

Max Activating Token Index: 279