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

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

Neuron 960 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1906. Min Range: -4.1906

Max Act: 4.1454. Min Act: -0.0000

Data Index: 405078 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 4.1906. Min Range: -4.1906

Max Act: 4.0481. Min Act: -0.0000

Data Index: 1144058 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 4.1906. Min Range: -4.1906

Max Act: 3.8413. Min Act: -0.0000

Data Index: 981665 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 4.1906. Min Range: -4.1906

Max Act: 4.1906. Min Act: -0.0000

Data Index: 172852 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 4.1906. Min Range: -4.1906

Max Act: 3.7968. Min Act: -0.0000

Data Index: 490472 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 4.1906. Min Range: -4.1906

Max Act: 3.9233. Min Act: -0.0000

Data Index: 422469 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 4.1906. Min Range: -4.1906

Max Act: 3.7375. Min Act: -0.0000

Data Index: 660028 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 4.1906. Min Range: -4.1906

Max Act: 3.7532. Min Act: -0.0000

Data Index: 987586 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 4.1906. Min Range: -4.1906

Max Act: 4.0639. Min Act: -0.0000

Data Index: 1034523 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 4.1906. Min Range: -4.1906

Max Act: 3.7170. Min Act: -0.0000

Data Index: 1163272 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 4.1906. Min Range: -4.1906

Max Act: 3.5285. Min Act: -0.0000

Data Index: 1221934 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 4.1906. Min Range: -4.1906

Max Act: 3.8629. Min Act: -0.0000

Data Index: 1068187 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 4.1906. Min Range: -4.1906

Max Act: 3.3522. Min Act: -0.0000

Data Index: 846200 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 4.1906. Min Range: -4.1906

Max Act: 3.4884. Min Act: -0.0000

Data Index: 125687 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 4.1906. Min Range: -4.1906

Max Act: 3.6617. Min Act: -0.0000

Data Index: 568530 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 4.1906. Min Range: -4.1906

Max Act: 3.6305. Min Act: -0.0000

Data Index: 861495 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 4.1906. Min Range: -4.1906

Max Act: 3.5739. Min Act: -0.0000

Data Index: 117552 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 4.1906. Min Range: -4.1906

Max Act: 3.6947. Min Act: -0.0000

Data Index: 20556 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 4.1906. Min Range: -4.1906

Max Act: 3.4978. Min Act: -0.0000

Data Index: 291960 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 4.1906. Min Range: -4.1906

Max Act: 3.4756. Min Act: -0.0000

Data Index: 1025160 (C4 (Web Text))

Max Activating Token Index: 80