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

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

Neuron 4973 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: 2.0184. Min Range: -2.0184

Max Act: 2.0184. Min Act: -0.0000

Data Index: 994682 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 2.0184. Min Range: -2.0184

Max Act: 1.7584. Min Act: -0.0000

Data Index: 1184962 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 2.0184. Min Range: -2.0184

Max Act: 1.5543. Min Act: -0.0000

Data Index: 18387 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 2.0184. Min Range: -2.0184

Max Act: 1.6320. Min Act: -0.0000

Data Index: 1387903 (Python Code)

Max Activating Token Index: 1007

Text #4

Max Range: 2.0184. Min Range: -2.0184

Max Act: 1.6896. Min Act: -0.0000

Data Index: 1137707 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 2.0184. Min Range: -2.0184

Max Act: 1.6769. Min Act: -0.0000

Data Index: 1548082 (Python Code)

Max Activating Token Index: 273

Text #6

Max Range: 2.0184. Min Range: -2.0184

Max Act: 1.6635. Min Act: -0.0000

Data Index: 640747 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 2.0184. Min Range: -2.0184

Max Act: 1.5369. Min Act: -0.0000

Data Index: 1000556 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 2.0184. Min Range: -2.0184

Max Act: 1.5403. Min Act: -0.0000

Data Index: 23957 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 2.0184. Min Range: -2.0184

Max Act: 1.6312. Min Act: -0.0000

Data Index: 402239 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 2.0184. Min Range: -2.0184

Max Act: 1.5877. Min Act: -0.0000

Data Index: 9955 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 2.0184. Min Range: -2.0184

Max Act: 1.4790. Min Act: -0.0000

Data Index: 1195575 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 2.0184. Min Range: -2.0184

Max Act: 1.6426. Min Act: -0.0000

Data Index: 350970 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 2.0184. Min Range: -2.0184

Max Act: 1.4660. Min Act: -0.0000

Data Index: 763136 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 2.0184. Min Range: -2.0184

Max Act: 1.4463. Min Act: -0.0000

Data Index: 780765 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 2.0184. Min Range: -2.0184

Max Act: 1.4260. Min Act: -0.0000

Data Index: 815336 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 2.0184. Min Range: -2.0184

Max Act: 1.5053. Min Act: -0.0000

Data Index: 1038523 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 2.0184. Min Range: -2.0184

Max Act: 1.3217. Min Act: -0.0000

Data Index: 252342 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 2.0184. Min Range: -2.0184

Max Act: 1.4339. Min Act: -0.0000

Data Index: 1408824 (Python Code)

Max Activating Token Index: 502

Text #19

Max Range: 2.0184. Min Range: -2.0184

Max Act: 1.4037. Min Act: -0.0000

Data Index: 469001 (C4 (Web Text))

Max Activating Token Index: 125