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

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

Neuron 2677 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: 1.8826. Min Range: -1.8826

Max Act: 1.8816. Min Act: -0.0001

Data Index: 1092711 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.8826. Min Act: -0.0001

Data Index: 807394 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.4471. Min Act: -0.0001

Data Index: 354383 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.2705. Min Act: -0.0000

Data Index: 485441 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.1113. Min Act: -0.0000

Data Index: 339365 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.3047. Min Act: -0.0001

Data Index: 401142 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.2458. Min Act: -0.0000

Data Index: 785050 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.1407. Min Act: -0.0001

Data Index: 1201351 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.2760. Min Act: -0.0000

Data Index: 436288 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.2964. Min Act: -0.0001

Data Index: 512808 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.1586. Min Act: -0.0001

Data Index: 67656 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.1290. Min Act: -0.0000

Data Index: 907508 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.1597. Min Act: -0.0001

Data Index: 438283 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.0775. Min Act: -0.0001

Data Index: 1095209 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.0199. Min Act: -0.0000

Data Index: 1306983 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.0545. Min Act: -0.0001

Data Index: 390505 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.1064. Min Act: -0.0001

Data Index: 1194051 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.0751. Min Act: -0.0000

Data Index: 191716 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.0150. Min Act: -0.0000

Data Index: 25481 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.1392. Min Act: -0.0001

Data Index: 764373 (C4 (Web Text))

Max Activating Token Index: 688