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

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

Neuron 217 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3389. Min Range: -7.3389

Max Act: 7.3389. Min Act: -0.0001

Data Index: 1131910 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 7.3389. Min Range: -7.3389

Max Act: 6.2015. Min Act: -0.0001

Data Index: 639896 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 7.3389. Min Range: -7.3389

Max Act: 6.2545. Min Act: -0.0001

Data Index: 501839 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 7.3389. Min Range: -7.3389

Max Act: 5.4761. Min Act: -0.0001

Data Index: 1276166 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 7.3389. Min Range: -7.3389

Max Act: 5.7847. Min Act: -0.0001

Data Index: 1052232 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 7.3389. Min Range: -7.3389

Max Act: 5.7762. Min Act: -0.0001

Data Index: 92290 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 7.3389. Min Range: -7.3389

Max Act: 5.8718. Min Act: -0.0001

Data Index: 1232008 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 7.3389. Min Range: -7.3389

Max Act: 5.5070. Min Act: -0.0001

Data Index: 1222171 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 7.3389. Min Range: -7.3389

Max Act: 5.7810. Min Act: -0.0001

Data Index: 473490 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 7.3389. Min Range: -7.3389

Max Act: 5.8854. Min Act: -0.0001

Data Index: 1106345 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 7.3389. Min Range: -7.3389

Max Act: 5.3956. Min Act: -0.0001

Data Index: 191858 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 7.3389. Min Range: -7.3389

Max Act: 5.3693. Min Act: -0.0001

Data Index: 262967 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 7.3389. Min Range: -7.3389

Max Act: 5.1465. Min Act: -0.0001

Data Index: 357177 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 7.3389. Min Range: -7.3389

Max Act: 5.2002. Min Act: -0.0001

Data Index: 198686 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 7.3389. Min Range: -7.3389

Max Act: 5.0778. Min Act: -0.0001

Data Index: 1333885 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 7.3389. Min Range: -7.3389

Max Act: 5.0612. Min Act: -0.0001

Data Index: 30221 (C4 (Web Text))

Max Activating Token Index: 415

Text #16

Max Range: 7.3389. Min Range: -7.3389

Max Act: 5.0296. Min Act: -0.0001

Data Index: 941050 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 7.3389. Min Range: -7.3389

Max Act: 4.6387. Min Act: -0.0001

Data Index: 239271 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 7.3389. Min Range: -7.3389

Max Act: 5.0022. Min Act: -0.0001

Data Index: 793876 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 7.3389. Min Range: -7.3389

Max Act: 5.0278. Min Act: -0.0001

Data Index: 515748 (C4 (Web Text))

Max Activating Token Index: 662