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

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

Neuron 1606 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.4624. Min Act: 0.0000

Data Index: 271189 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.2903. Min Act: 0.0000

Data Index: 272144 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.1727. Min Act: 0.0000

Data Index: 955624 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.1353. Min Act: 0.0001

Data Index: 51785 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.0227. Min Act: 0.0001

Data Index: 1227650 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 1.4624. Min Range: -1.4624

Max Act: 0.9493. Min Act: 0.0000

Data Index: 1113983 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 1.4624. Min Range: -1.4624

Max Act: 0.9032. Min Act: 0.0001

Data Index: 710680 (C4 (Web Text))

Max Activating Token Index: 924

Text #7

Max Range: 1.4624. Min Range: -1.4624

Max Act: 0.9182. Min Act: -0.0000

Data Index: 726614 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 1.4624. Min Range: -1.4624

Max Act: 0.9166. Min Act: 0.0000

Data Index: 44736 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 1.4624. Min Range: -1.4624

Max Act: 0.8524. Min Act: -0.0000

Data Index: 112272 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 1.4624. Min Range: -1.4624

Max Act: 0.9030. Min Act: 0.0000

Data Index: 171691 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 1.4624. Min Range: -1.4624

Max Act: 0.8617. Min Act: -0.0000

Data Index: 682610 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 1.4624. Min Range: -1.4624

Max Act: 0.8810. Min Act: -0.0000

Data Index: 1207518 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 1.4624. Min Range: -1.4624

Max Act: 0.7552. Min Act: 0.0000

Data Index: 1288517 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 1.4624. Min Range: -1.4624

Max Act: 0.9101. Min Act: 0.0000

Data Index: 1301158 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 1.4624. Min Range: -1.4624

Max Act: 0.8509. Min Act: -0.0000

Data Index: 848276 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 1.4624. Min Range: -1.4624

Max Act: 0.9100. Min Act: -0.0000

Data Index: 895839 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 1.4624. Min Range: -1.4624

Max Act: 0.8443. Min Act: 0.0001

Data Index: 880440 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 1.4624. Min Range: -1.4624

Max Act: 0.9031. Min Act: -0.0000

Data Index: 76099 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 1.4624. Min Range: -1.4624

Max Act: 0.7676. Min Act: -0.0000

Data Index: 558438 (C4 (Web Text))

Max Activating Token Index: 36