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

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

Neuron 4905 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.9768. Min Range: -6.9768

Max Act: 6.9660. Min Act: -0.0001

Data Index: 318859 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 6.9768. Min Range: -6.9768

Max Act: 6.9768. Min Act: -0.0001

Data Index: 1054476 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 6.9768. Min Range: -6.9768

Max Act: 6.5194. Min Act: -0.0001

Data Index: 752790 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 6.9768. Min Range: -6.9768

Max Act: 6.0958. Min Act: -0.0001

Data Index: 797154 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 6.9768. Min Range: -6.9768

Max Act: 5.7407. Min Act: -0.0001

Data Index: 528658 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 6.9768. Min Range: -6.9768

Max Act: 5.8113. Min Act: -0.0001

Data Index: 1316937 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 6.9768. Min Range: -6.9768

Max Act: 5.8122. Min Act: -0.0001

Data Index: 504644 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 6.9768. Min Range: -6.9768

Max Act: 5.7263. Min Act: -0.0001

Data Index: 54804 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 6.9768. Min Range: -6.9768

Max Act: 5.6199. Min Act: -0.0001

Data Index: 794984 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 6.9768. Min Range: -6.9768

Max Act: 6.1461. Min Act: -0.0001

Data Index: 713650 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 6.9768. Min Range: -6.9768

Max Act: 5.9114. Min Act: -0.0001

Data Index: 187050 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 6.9768. Min Range: -6.9768

Max Act: 5.3722. Min Act: -0.0001

Data Index: 1062382 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 6.9768. Min Range: -6.9768

Max Act: 5.6773. Min Act: -0.0001

Data Index: 1015878 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 6.9768. Min Range: -6.9768

Max Act: 5.4561. Min Act: -0.0001

Data Index: 167518 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 6.9768. Min Range: -6.9768

Max Act: 5.7524. Min Act: -0.0001

Data Index: 1176959 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 6.9768. Min Range: -6.9768

Max Act: 5.5423. Min Act: -0.0001

Data Index: 1258826 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 6.9768. Min Range: -6.9768

Max Act: 5.5231. Min Act: -0.0001

Data Index: 201580 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 6.9768. Min Range: -6.9768

Max Act: 5.3339. Min Act: -0.0001

Data Index: 494527 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 6.9768. Min Range: -6.9768

Max Act: 5.3178. Min Act: -0.0001

Data Index: 397685 (C4 (Web Text))

Max Activating Token Index: 652

Text #19

Max Range: 6.9768. Min Range: -6.9768

Max Act: 5.6679. Min Act: -0.0001

Data Index: 1042539 (C4 (Web Text))

Max Activating Token Index: 308