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

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

Neuron 2094 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: 0.3329. Min Range: -0.3329

Max Act: 0.3329. Min Act: -0.0001

Data Index: 723169 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.3195. Min Act: -0.0001

Data Index: 342853 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.3207. Min Act: -0.0001

Data Index: 298411 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.3058. Min Act: -0.0001

Data Index: 599467 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2850. Min Act: -0.0001

Data Index: 1313540 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.3026. Min Act: -0.0001

Data Index: 351265 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.3101. Min Act: -0.0001

Data Index: 671364 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.3060. Min Act: -0.0001

Data Index: 562658 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2910. Min Act: -0.0001

Data Index: 1198463 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2873. Min Act: -0.0001

Data Index: 126160 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2751. Min Act: -0.0001

Data Index: 1061785 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2845. Min Act: -0.0001

Data Index: 610172 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2834. Min Act: -0.0001

Data Index: 14495 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.3064. Min Act: -0.0001

Data Index: 1339848 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2788. Min Act: -0.0001

Data Index: 161846 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2792. Min Act: -0.0001

Data Index: 759832 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2688. Min Act: -0.0001

Data Index: 540843 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2737. Min Act: -0.0001

Data Index: 965518 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2818. Min Act: -0.0001

Data Index: 850365 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2678. Min Act: -0.0001

Data Index: 132592 (C4 (Web Text))

Max Activating Token Index: 7