Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2152 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.9077. Min Range: -3.9077

Max Act: 3.9077. Min Act: -0.0001

Data Index: 1298907 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 3.9077. Min Range: -3.9077

Max Act: 3.8391. Min Act: -0.0000

Data Index: 356016 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 3.9077. Min Range: -3.9077

Max Act: 3.6411. Min Act: -0.0000

Data Index: 1080652 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 3.9077. Min Range: -3.9077

Max Act: 3.3506. Min Act: -0.0001

Data Index: 1262987 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 3.9077. Min Range: -3.9077

Max Act: 3.4775. Min Act: -0.0000

Data Index: 237682 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 3.9077. Min Range: -3.9077

Max Act: 3.4486. Min Act: -0.0001

Data Index: 872187 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 3.9077. Min Range: -3.9077

Max Act: 3.0155. Min Act: -0.0001

Data Index: 1312528 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 3.9077. Min Range: -3.9077

Max Act: 3.1618. Min Act: -0.0001

Data Index: 411339 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 3.9077. Min Range: -3.9077

Max Act: 3.0112. Min Act: -0.0001

Data Index: 360847 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 3.9077. Min Range: -3.9077

Max Act: 2.6986. Min Act: -0.0001

Data Index: 866739 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 3.9077. Min Range: -3.9077

Max Act: 2.9462. Min Act: -0.0001

Data Index: 1252156 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 3.9077. Min Range: -3.9077

Max Act: 3.0615. Min Act: -0.0001

Data Index: 1348525 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 3.9077. Min Range: -3.9077

Max Act: 3.0483. Min Act: -0.0001

Data Index: 4925 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 3.9077. Min Range: -3.9077

Max Act: 2.8977. Min Act: -0.0001

Data Index: 1342924 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 3.9077. Min Range: -3.9077

Max Act: 3.1471. Min Act: -0.0000

Data Index: 1019072 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 3.9077. Min Range: -3.9077

Max Act: 3.0000. Min Act: -0.0000

Data Index: 1167577 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 3.9077. Min Range: -3.9077

Max Act: 2.9963. Min Act: -0.0000

Data Index: 473103 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 3.9077. Min Range: -3.9077

Max Act: 2.9832. Min Act: -0.0001

Data Index: 158331 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 3.9077. Min Range: -3.9077

Max Act: 2.8262. Min Act: -0.0001

Data Index: 1232344 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 3.9077. Min Range: -3.9077

Max Act: 2.9427. Min Act: -0.0001

Data Index: 1202398 (C4 (Web Text))

Max Activating Token Index: 74