Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2966 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9635. Min Range: -0.9635

Max Act: 0.9635. Min Act: -0.0000

Data Index: 1104051 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 0.9635. Min Range: -0.9635

Max Act: 0.8535. Min Act: -0.0000

Data Index: 1294579 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.9635. Min Range: -0.9635

Max Act: 0.8435. Min Act: -0.0000

Data Index: 420279 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.9635. Min Range: -0.9635

Max Act: 0.7962. Min Act: -0.0000

Data Index: 1127597 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 0.9635. Min Range: -0.9635

Max Act: 0.8628. Min Act: -0.0000

Data Index: 1255394 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 0.9635. Min Range: -0.9635

Max Act: 0.7924. Min Act: -0.0000

Data Index: 204230 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 0.9635. Min Range: -0.9635

Max Act: 0.7276. Min Act: -0.0000

Data Index: 471597 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 0.9635. Min Range: -0.9635

Max Act: 0.7416. Min Act: -0.0000

Data Index: 773228 (C4 (Web Text))

Max Activating Token Index: 394

Text #8

Max Range: 0.9635. Min Range: -0.9635

Max Act: 0.7785. Min Act: -0.0000

Data Index: 626838 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 0.9635. Min Range: -0.9635

Max Act: 0.7853. Min Act: -0.0000

Data Index: 1128348 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 0.9635. Min Range: -0.9635

Max Act: 0.6982. Min Act: -0.0000

Data Index: 1054999 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.9635. Min Range: -0.9635

Max Act: 0.7121. Min Act: -0.0000

Data Index: 575981 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 0.9635. Min Range: -0.9635

Max Act: 0.7203. Min Act: -0.0000

Data Index: 81229 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 0.9635. Min Range: -0.9635

Max Act: 0.7060. Min Act: -0.0000

Data Index: 1178354 (C4 (Web Text))

Max Activating Token Index: 660

Text #14

Max Range: 0.9635. Min Range: -0.9635

Max Act: 0.7863. Min Act: -0.0000

Data Index: 358814 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 0.9635. Min Range: -0.9635

Max Act: 0.7587. Min Act: -0.0000

Data Index: 420236 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.9635. Min Range: -0.9635

Max Act: 0.6452. Min Act: -0.0000

Data Index: 1022737 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 0.9635. Min Range: -0.9635

Max Act: 0.6745. Min Act: -0.0000

Data Index: 610453 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 0.9635. Min Range: -0.9635

Max Act: 0.6624. Min Act: -0.0000

Data Index: 798699 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 0.9635. Min Range: -0.9635

Max Act: 0.6971. Min Act: -0.0000

Data Index: 1204596 (C4 (Web Text))

Max Activating Token Index: 805