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

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

Neuron 1881 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.3469. Min Range: -3.3469

Max Act: 3.3469. Min Act: -0.0000

Data Index: 482837 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 3.3469. Min Range: -3.3469

Max Act: 2.6821. Min Act: -0.0000

Data Index: 707343 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 3.3469. Min Range: -3.3469

Max Act: 2.5451. Min Act: -0.0000

Data Index: 1120384 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 3.3469. Min Range: -3.3469

Max Act: 2.6406. Min Act: -0.0000

Data Index: 1256667 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 3.3469. Min Range: -3.3469

Max Act: 2.5902. Min Act: -0.0000

Data Index: 728479 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 3.3469. Min Range: -3.3469

Max Act: 2.3678. Min Act: -0.0000

Data Index: 1111109 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 3.3469. Min Range: -3.3469

Max Act: 2.4102. Min Act: -0.0000

Data Index: 450470 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 3.3469. Min Range: -3.3469

Max Act: 2.2620. Min Act: -0.0000

Data Index: 953770 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 3.3469. Min Range: -3.3469

Max Act: 2.2080. Min Act: -0.0000

Data Index: 84653 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 3.3469. Min Range: -3.3469

Max Act: 2.2249. Min Act: -0.0000

Data Index: 78140 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 3.3469. Min Range: -3.3469

Max Act: 2.1680. Min Act: -0.0000

Data Index: 710887 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 3.3469. Min Range: -3.3469

Max Act: 2.2488. Min Act: -0.0000

Data Index: 259523 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 3.3469. Min Range: -3.3469

Max Act: 2.1021. Min Act: -0.0000

Data Index: 393537 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 3.3469. Min Range: -3.3469

Max Act: 2.0596. Min Act: -0.0000

Data Index: 686331 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 3.3469. Min Range: -3.3469

Max Act: 2.0142. Min Act: -0.0000

Data Index: 237942 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 3.3469. Min Range: -3.3469

Max Act: 1.8944. Min Act: -0.0000

Data Index: 440913 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 3.3469. Min Range: -3.3469

Max Act: 1.9853. Min Act: -0.0000

Data Index: 625740 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 3.3469. Min Range: -3.3469

Max Act: 1.9831. Min Act: -0.0000

Data Index: 630877 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 3.3469. Min Range: -3.3469

Max Act: 1.8552. Min Act: -0.0000

Data Index: 1110603 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 3.3469. Min Range: -3.3469

Max Act: 1.8481. Min Act: -0.0000

Data Index: 84479 (C4 (Web Text))

Max Activating Token Index: 476