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

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

Neuron 3735 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.4202. Min Act: -0.0000

Data Index: 653569 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.4409. Min Act: -0.0000

Data Index: 435211 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.4450. Min Act: -0.0000

Data Index: 208587 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.4154. Min Act: -0.0000

Data Index: 383792 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.4053. Min Act: -0.0000

Data Index: 1040593 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3844. Min Act: -0.0000

Data Index: 868361 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3977. Min Act: -0.0000

Data Index: 662738 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3901. Min Act: -0.0000

Data Index: 524934 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3994. Min Act: -0.0000

Data Index: 316350 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3767. Min Act: -0.0000

Data Index: 202195 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3334. Min Act: -0.0000

Data Index: 19120 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3796. Min Act: -0.0000

Data Index: 752533 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.4085. Min Act: -0.0000

Data Index: 356278 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3729. Min Act: -0.0000

Data Index: 297388 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3580. Min Act: -0.0000

Data Index: 1227494 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3498. Min Act: -0.0000

Data Index: 675540 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3784. Min Act: -0.0000

Data Index: 621946 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3533. Min Act: -0.0000

Data Index: 160911 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3600. Min Act: -0.0000

Data Index: 967030 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 0.4450. Min Range: -0.4450

Max Act: 0.3382. Min Act: -0.0000

Data Index: 158929 (C4 (Web Text))

Max Activating Token Index: 873