Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 500 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0489. Min Act: -0.0006

Data Index: 1217759 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0469. Min Act: -0.0005

Data Index: 735721 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0475. Min Act: -0.0005

Data Index: 1319871 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0460. Min Act: -0.0006

Data Index: 154220 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0439. Min Act: -0.0005

Data Index: 138288 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0444. Min Act: -0.0005

Data Index: 3944 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0443. Min Act: -0.0006

Data Index: 64152 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0438. Min Act: -0.0006

Data Index: 266126 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0440. Min Act: -0.0006

Data Index: 902697 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0438. Min Act: -0.0006

Data Index: 173139 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0445. Min Act: -0.0005

Data Index: 1140686 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0435. Min Act: -0.0006

Data Index: 697534 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0433. Min Act: -0.0005

Data Index: 732260 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0430. Min Act: -0.0006

Data Index: 1232032 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0430. Min Act: -0.0006

Data Index: 435147 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0427. Min Act: -0.0005

Data Index: 621259 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0427. Min Act: -0.0006

Data Index: 163192 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0422. Min Act: -0.0006

Data Index: 394923 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0423. Min Act: -0.0005

Data Index: 191837 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0424. Min Act: -0.0005

Data Index: 1005148 (C4 (Web Text))

Max Activating Token Index: 987