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

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

Neuron 3798 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: 7.3967. Min Range: -7.3967

Max Act: 7.3967. Min Act: -0.0001

Data Index: 1271201 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 7.3967. Min Range: -7.3967

Max Act: 5.9487. Min Act: -0.0001

Data Index: 307179 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 7.3967. Min Range: -7.3967

Max Act: 6.2892. Min Act: -0.0001

Data Index: 1332068 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 7.3967. Min Range: -7.3967

Max Act: 6.1850. Min Act: -0.0001

Data Index: 176390 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 7.3967. Min Range: -7.3967

Max Act: 5.6520. Min Act: -0.0001

Data Index: 97021 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 7.3967. Min Range: -7.3967

Max Act: 5.6301. Min Act: -0.0001

Data Index: 581049 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 7.3967. Min Range: -7.3967

Max Act: 5.5770. Min Act: -0.0001

Data Index: 113921 (C4 (Web Text))

Max Activating Token Index: 484

Text #7

Max Range: 7.3967. Min Range: -7.3967

Max Act: 5.4525. Min Act: -0.0001

Data Index: 378623 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 7.3967. Min Range: -7.3967

Max Act: 5.3678. Min Act: -0.0001

Data Index: 14776 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 7.3967. Min Range: -7.3967

Max Act: 5.1488. Min Act: -0.0001

Data Index: 1048397 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 7.3967. Min Range: -7.3967

Max Act: 5.4863. Min Act: -0.0001

Data Index: 992326 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 7.3967. Min Range: -7.3967

Max Act: 5.8170. Min Act: -0.0001

Data Index: 233596 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 7.3967. Min Range: -7.3967

Max Act: 5.2598. Min Act: -0.0001

Data Index: 159604 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 7.3967. Min Range: -7.3967

Max Act: 5.0497. Min Act: -0.0001

Data Index: 625740 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 7.3967. Min Range: -7.3967

Max Act: 5.2540. Min Act: -0.0001

Data Index: 1205270 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 7.3967. Min Range: -7.3967

Max Act: 4.7296. Min Act: -0.0001

Data Index: 211735 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 7.3967. Min Range: -7.3967

Max Act: 5.3443. Min Act: -0.0001

Data Index: 976372 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 7.3967. Min Range: -7.3967

Max Act: 5.0042. Min Act: -0.0001

Data Index: 352512 (C4 (Web Text))

Max Activating Token Index: 966

Text #18

Max Range: 7.3967. Min Range: -7.3967

Max Act: 4.9668. Min Act: -0.0001

Data Index: 68060 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 7.3967. Min Range: -7.3967

Max Act: 4.9219. Min Act: -0.0001

Data Index: 586890 (C4 (Web Text))

Max Activating Token Index: 1015