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

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

Neuron 3922 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: 5.2434. Min Range: -5.2434

Max Act: 5.1161. Min Act: -0.0000

Data Index: 981060 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 5.2434. Min Range: -5.2434

Max Act: 5.0497. Min Act: -0.0000

Data Index: 774888 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 5.2434. Min Range: -5.2434

Max Act: 5.2434. Min Act: -0.0000

Data Index: 247252 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 5.2434. Min Range: -5.2434

Max Act: 3.9059. Min Act: -0.0000

Data Index: 1159086 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 5.2434. Min Range: -5.2434

Max Act: 3.9710. Min Act: -0.0000

Data Index: 405404 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 5.2434. Min Range: -5.2434

Max Act: 4.0611. Min Act: -0.0000

Data Index: 1102382 (C4 (Web Text))

Max Activating Token Index: 1022

Text #6

Max Range: 5.2434. Min Range: -5.2434

Max Act: 3.9901. Min Act: -0.0000

Data Index: 181760 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 5.2434. Min Range: -5.2434

Max Act: 3.8206. Min Act: -0.0000

Data Index: 1098179 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 5.2434. Min Range: -5.2434

Max Act: 3.5425. Min Act: -0.0000

Data Index: 1130699 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 5.2434. Min Range: -5.2434

Max Act: 3.5207. Min Act: -0.0000

Data Index: 357351 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 5.2434. Min Range: -5.2434

Max Act: 3.3400. Min Act: -0.0000

Data Index: 25267 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 5.2434. Min Range: -5.2434

Max Act: 3.1554. Min Act: -0.0000

Data Index: 1033904 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 5.2434. Min Range: -5.2434

Max Act: 3.2935. Min Act: -0.0000

Data Index: 553063 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 5.2434. Min Range: -5.2434

Max Act: 2.9862. Min Act: -0.0000

Data Index: 1203845 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 5.2434. Min Range: -5.2434

Max Act: 3.4319. Min Act: -0.0000

Data Index: 239557 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 5.2434. Min Range: -5.2434

Max Act: 2.8626. Min Act: -0.0000

Data Index: 226092 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 5.2434. Min Range: -5.2434

Max Act: 3.1431. Min Act: -0.0000

Data Index: 558439 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 5.2434. Min Range: -5.2434

Max Act: 2.7798. Min Act: -0.0000

Data Index: 422118 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 5.2434. Min Range: -5.2434

Max Act: 2.9485. Min Act: -0.0000

Data Index: 410195 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 5.2434. Min Range: -5.2434

Max Act: 2.9076. Min Act: -0.0000

Data Index: 618431 (C4 (Web Text))

Max Activating Token Index: 256