Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4081 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.2142. Min Act: -0.0000

Data Index: 1425400 (Python Code)

Max Activating Token Index: 169

Text #1

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.0198. Min Act: -0.0000

Data Index: 1429798 (Python Code)

Max Activating Token Index: 394

Text #2

Max Range: 1.2142. Min Range: -1.2142

Max Act: 0.7762. Min Act: -0.0000

Data Index: 1471141 (Python Code)

Max Activating Token Index: 99

Text #3

Max Range: 1.2142. Min Range: -1.2142

Max Act: 0.8431. Min Act: -0.0000

Data Index: 231777 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 1.2142. Min Range: -1.2142

Max Act: 0.8033. Min Act: -0.0000

Data Index: 1373367 (Python Code)

Max Activating Token Index: 352

Text #5

Max Range: 1.2142. Min Range: -1.2142

Max Act: 0.7841. Min Act: -0.0000

Data Index: 145790 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 1.2142. Min Range: -1.2142

Max Act: 0.7602. Min Act: -0.0000

Data Index: 1610362 (Python Code)

Max Activating Token Index: 787

Text #7

Max Range: 1.2142. Min Range: -1.2142

Max Act: 0.7625. Min Act: -0.0000

Data Index: 1310448 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 1.2142. Min Range: -1.2142

Max Act: 0.7677. Min Act: -0.0000

Data Index: 1415751 (Python Code)

Max Activating Token Index: 835

Text #9

Max Range: 1.2142. Min Range: -1.2142

Max Act: 0.7701. Min Act: -0.0000

Data Index: 1623077 (Python Code)

Max Activating Token Index: 135

Text #10

Max Range: 1.2142. Min Range: -1.2142

Max Act: 0.7416. Min Act: -0.0000

Data Index: 1294217 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 1.2142. Min Range: -1.2142

Max Act: 0.7390. Min Act: -0.0000

Data Index: 1119646 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 1.2142. Min Range: -1.2142

Max Act: 0.7615. Min Act: -0.0000

Data Index: 527691 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 1.2142. Min Range: -1.2142

Max Act: 0.7603. Min Act: -0.0000

Data Index: 889143 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 1.2142. Min Range: -1.2142

Max Act: 0.7505. Min Act: -0.0000

Data Index: 1457803 (Python Code)

Max Activating Token Index: 626

Text #15

Max Range: 1.2142. Min Range: -1.2142

Max Act: 0.7527. Min Act: -0.0000

Data Index: 1391946 (Python Code)

Max Activating Token Index: 146

Text #16

Max Range: 1.2142. Min Range: -1.2142

Max Act: 0.7053. Min Act: -0.0000

Data Index: 338588 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 1.2142. Min Range: -1.2142

Max Act: 0.7196. Min Act: -0.0000

Data Index: 912291 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 1.2142. Min Range: -1.2142

Max Act: 0.7438. Min Act: -0.0000

Data Index: 250631 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 1.2142. Min Range: -1.2142

Max Act: 0.7086. Min Act: -0.0000

Data Index: 1340218 (C4 (Web Text))

Max Activating Token Index: 843