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

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

Neuron 3216 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: 0.5662. Min Range: -0.5662

Max Act: 0.5662. Min Act: -0.0000

Data Index: 1323749 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.4664. Min Act: -0.0000

Data Index: 655392 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.4210. Min Act: -0.0000

Data Index: 1061280 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.4076. Min Act: -0.0000

Data Index: 684819 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.4053. Min Act: -0.0000

Data Index: 718653 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.3661. Min Act: -0.0000

Data Index: 118173 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.3884. Min Act: -0.0000

Data Index: 535435 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.3833. Min Act: -0.0000

Data Index: 1297905 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.3524. Min Act: -0.0000

Data Index: 434185 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.3462. Min Act: -0.0000

Data Index: 1199312 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.3679. Min Act: -0.0000

Data Index: 649509 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.3786. Min Act: -0.0001

Data Index: 1271007 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.3620. Min Act: -0.0001

Data Index: 1026190 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.3530. Min Act: -0.0000

Data Index: 599512 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.3592. Min Act: -0.0000

Data Index: 707481 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.3436. Min Act: -0.0000

Data Index: 372785 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.3235. Min Act: -0.0000

Data Index: 208779 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.3162. Min Act: -0.0000

Data Index: 1214054 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.3686. Min Act: -0.0000

Data Index: 1356725 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.3536. Min Act: -0.0000

Data Index: 116183 (C4 (Web Text))

Max Activating Token Index: 809