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

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

Neuron 4276 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5947. Min Range: -2.5947

Max Act: 2.5947. Min Act: -0.0000

Data Index: 590690 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 2.5947. Min Range: -2.5947

Max Act: 2.3276. Min Act: -0.0000

Data Index: 812592 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 2.5947. Min Range: -2.5947

Max Act: 2.2344. Min Act: -0.0000

Data Index: 923852 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 2.5947. Min Range: -2.5947

Max Act: 2.0914. Min Act: -0.0000

Data Index: 900451 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 2.5947. Min Range: -2.5947

Max Act: 1.9805. Min Act: -0.0000

Data Index: 1318141 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 2.5947. Min Range: -2.5947

Max Act: 2.0387. Min Act: -0.0000

Data Index: 1273326 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 2.5947. Min Range: -2.5947

Max Act: 1.8795. Min Act: -0.0000

Data Index: 624412 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 2.5947. Min Range: -2.5947

Max Act: 1.8749. Min Act: -0.0000

Data Index: 402554 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 2.5947. Min Range: -2.5947

Max Act: 1.7272. Min Act: -0.0000

Data Index: 476166 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 2.5947. Min Range: -2.5947

Max Act: 1.7965. Min Act: -0.0000

Data Index: 612259 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 2.5947. Min Range: -2.5947

Max Act: 1.6210. Min Act: -0.0000

Data Index: 1275657 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 2.5947. Min Range: -2.5947

Max Act: 1.6869. Min Act: -0.0000

Data Index: 786243 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 2.5947. Min Range: -2.5947

Max Act: 1.6475. Min Act: -0.0000

Data Index: 1167707 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 2.5947. Min Range: -2.5947

Max Act: 1.6464. Min Act: -0.0000

Data Index: 156594 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 2.5947. Min Range: -2.5947

Max Act: 1.7009. Min Act: -0.0000

Data Index: 212777 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 2.5947. Min Range: -2.5947

Max Act: 1.6167. Min Act: -0.0000

Data Index: 214660 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 2.5947. Min Range: -2.5947

Max Act: 1.6166. Min Act: -0.0000

Data Index: 1279436 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 2.5947. Min Range: -2.5947

Max Act: 1.7021. Min Act: -0.0000

Data Index: 466861 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 2.5947. Min Range: -2.5947

Max Act: 1.5828. Min Act: -0.0000

Data Index: 1235177 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 2.5947. Min Range: -2.5947

Max Act: 1.5668. Min Act: -0.0000

Data Index: 606170 (C4 (Web Text))

Max Activating Token Index: 998