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

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

Neuron 113 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2066. Min Range: -3.2066

Max Act: 3.2066. Min Act: -0.0000

Data Index: 539192 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 3.2066. Min Range: -3.2066

Max Act: 1.8966. Min Act: -0.0000

Data Index: 590284 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 3.2066. Min Range: -3.2066

Max Act: 2.0668. Min Act: -0.0000

Data Index: 888529 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 3.2066. Min Range: -3.2066

Max Act: 1.8095. Min Act: -0.0000

Data Index: 637534 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 3.2066. Min Range: -3.2066

Max Act: 1.8684. Min Act: -0.0000

Data Index: 276275 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 3.2066. Min Range: -3.2066

Max Act: 1.8510. Min Act: -0.0000

Data Index: 12019 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 3.2066. Min Range: -3.2066

Max Act: 1.8406. Min Act: -0.0000

Data Index: 810454 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 3.2066. Min Range: -3.2066

Max Act: 1.7866. Min Act: -0.0000

Data Index: 565338 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 3.2066. Min Range: -3.2066

Max Act: 1.5687. Min Act: -0.0000

Data Index: 1071510 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 3.2066. Min Range: -3.2066

Max Act: 1.5080. Min Act: -0.0000

Data Index: 355102 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 3.2066. Min Range: -3.2066

Max Act: 1.6714. Min Act: -0.0000

Data Index: 379517 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 3.2066. Min Range: -3.2066

Max Act: 1.5631. Min Act: -0.0000

Data Index: 248216 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 3.2066. Min Range: -3.2066

Max Act: 1.4060. Min Act: -0.0000

Data Index: 636378 (C4 (Web Text))

Max Activating Token Index: 1018

Text #13

Max Range: 3.2066. Min Range: -3.2066

Max Act: 1.5431. Min Act: -0.0000

Data Index: 1154108 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 3.2066. Min Range: -3.2066

Max Act: 1.5093. Min Act: -0.0000

Data Index: 1309763 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 3.2066. Min Range: -3.2066

Max Act: 1.7614. Min Act: -0.0000

Data Index: 1068314 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 3.2066. Min Range: -3.2066

Max Act: 1.3814. Min Act: -0.0000

Data Index: 305474 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 3.2066. Min Range: -3.2066

Max Act: 1.4587. Min Act: -0.0000

Data Index: 1184679 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 3.2066. Min Range: -3.2066

Max Act: 1.4273. Min Act: -0.0000

Data Index: 276309 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 3.2066. Min Range: -3.2066

Max Act: 1.4985. Min Act: -0.0000

Data Index: 805311 (C4 (Web Text))

Max Activating Token Index: 48