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

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

Neuron 2186 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.8072. Min Act: -0.0001

Data Index: 185150 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.7817. Min Act: -0.0001

Data Index: 658956 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.7068. Min Act: -0.0002

Data Index: 1253686 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.6416. Min Act: -0.0001

Data Index: 1004036 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.7188. Min Act: -0.0001

Data Index: 162174 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.7403. Min Act: -0.0002

Data Index: 97132 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.6034. Min Act: -0.0001

Data Index: 826905 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.6668. Min Act: -0.0001

Data Index: 616013 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.5819. Min Act: -0.0002

Data Index: 381473 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.5388. Min Act: -0.0001

Data Index: 1050881 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.5934. Min Act: -0.0002

Data Index: 318926 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.5977. Min Act: -0.0001

Data Index: 1220363 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.5621. Min Act: -0.0002

Data Index: 744299 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.6370. Min Act: -0.0002

Data Index: 320477 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.5413. Min Act: -0.0001

Data Index: 1001801 (C4 (Web Text))

Max Activating Token Index: 484

Text #15

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.6119. Min Act: -0.0002

Data Index: 514548 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.5160. Min Act: -0.0001

Data Index: 1013715 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.5881. Min Act: -0.0002

Data Index: 934374 (C4 (Web Text))

Max Activating Token Index: 834

Text #18

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.6168. Min Act: -0.0001

Data Index: 1013203 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.5590. Min Act: -0.0002

Data Index: 1268686 (C4 (Web Text))

Max Activating Token Index: 838