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

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

Neuron 3942 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: 2.7485. Min Range: -2.7485

Max Act: 2.7485. Min Act: -0.0000

Data Index: 125114 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 2.7485. Min Range: -2.7485

Max Act: 2.6388. Min Act: -0.0000

Data Index: 165600 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 2.7485. Min Range: -2.7485

Max Act: 2.5136. Min Act: -0.0000

Data Index: 676719 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 2.7485. Min Range: -2.7485

Max Act: 2.4292. Min Act: -0.0000

Data Index: 375634 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 2.7485. Min Range: -2.7485

Max Act: 2.2114. Min Act: -0.0000

Data Index: 1102169 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 2.7485. Min Range: -2.7485

Max Act: 2.3546. Min Act: -0.0000

Data Index: 426273 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 2.7485. Min Range: -2.7485

Max Act: 2.1217. Min Act: -0.0000

Data Index: 394670 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 2.7485. Min Range: -2.7485

Max Act: 2.0077. Min Act: -0.0000

Data Index: 219062 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 2.7485. Min Range: -2.7485

Max Act: 2.2054. Min Act: -0.0000

Data Index: 417508 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 2.7485. Min Range: -2.7485

Max Act: 1.7422. Min Act: -0.0000

Data Index: 867797 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 2.7485. Min Range: -2.7485

Max Act: 1.9399. Min Act: -0.0000

Data Index: 79438 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 2.7485. Min Range: -2.7485

Max Act: 2.0275. Min Act: -0.0000

Data Index: 120079 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 2.7485. Min Range: -2.7485

Max Act: 1.8670. Min Act: -0.0000

Data Index: 533687 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 2.7485. Min Range: -2.7485

Max Act: 1.8040. Min Act: -0.0000

Data Index: 148961 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 2.7485. Min Range: -2.7485

Max Act: 1.7740. Min Act: -0.0000

Data Index: 1147509 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 2.7485. Min Range: -2.7485

Max Act: 1.7627. Min Act: -0.0000

Data Index: 204109 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 2.7485. Min Range: -2.7485

Max Act: 1.7583. Min Act: -0.0000

Data Index: 25827 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 2.7485. Min Range: -2.7485

Max Act: 1.7529. Min Act: -0.0000

Data Index: 1196208 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 2.7485. Min Range: -2.7485

Max Act: 1.7394. Min Act: -0.0000

Data Index: 671103 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 2.7485. Min Range: -2.7485

Max Act: 1.8401. Min Act: -0.0000

Data Index: 1303582 (C4 (Web Text))

Max Activating Token Index: 987