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

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

Neuron 2940 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: 0.3820. Min Range: -0.3820

Max Act: 0.3667. Min Act: -0.0000

Data Index: 1325267 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3820. Min Act: -0.0000

Data Index: 633136 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3799. Min Act: -0.0000

Data Index: 363657 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3422. Min Act: 0.0001

Data Index: 1149460 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3287. Min Act: -0.0000

Data Index: 252603 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3315. Min Act: -0.0000

Data Index: 107649 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3037. Min Act: -0.0000

Data Index: 332971 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2787. Min Act: -0.0000

Data Index: 78638 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2969. Min Act: -0.0000

Data Index: 821566 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3156. Min Act: -0.0000

Data Index: 268373 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2957. Min Act: -0.0000

Data Index: 65205 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2918. Min Act: -0.0000

Data Index: 877389 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2989. Min Act: 0.0000

Data Index: 387519 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3043. Min Act: -0.0000

Data Index: 1138717 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3085. Min Act: -0.0000

Data Index: 52312 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2600. Min Act: -0.0000

Data Index: 1119761 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2880. Min Act: 0.0000

Data Index: 474860 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2823. Min Act: -0.0000

Data Index: 665891 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2794. Min Act: 0.0001

Data Index: 164218 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2874. Min Act: -0.0000

Data Index: 1126846 (C4 (Web Text))

Max Activating Token Index: 824