Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 297 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3588. Min Act: -0.0001

Data Index: 233880 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3186. Min Act: -0.0001

Data Index: 389411 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3036. Min Act: -0.0001

Data Index: 487046 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3113. Min Act: -0.0001

Data Index: 685691 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3093. Min Act: -0.0001

Data Index: 1346602 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2957. Min Act: -0.0001

Data Index: 1322447 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2716. Min Act: -0.0001

Data Index: 368659 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2742. Min Act: -0.0001

Data Index: 371516 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2756. Min Act: -0.0001

Data Index: 96250 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2879. Min Act: -0.0001

Data Index: 1070501 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2792. Min Act: -0.0001

Data Index: 437433 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3071. Min Act: -0.0001

Data Index: 1246906 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2765. Min Act: -0.0001

Data Index: 936891 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2640. Min Act: -0.0001

Data Index: 802334 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2632. Min Act: -0.0001

Data Index: 717835 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2810. Min Act: -0.0001

Data Index: 237712 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2691. Min Act: -0.0001

Data Index: 12464 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2680. Min Act: -0.0001

Data Index: 681653 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2576. Min Act: -0.0001

Data Index: 177602 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2762. Min Act: -0.0001

Data Index: 536540 (C4 (Web Text))

Max Activating Token Index: 400