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

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

Neuron 2008 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1206. Min Act: -0.0001

Data Index: 1097559 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1010. Min Act: -0.0001

Data Index: 919469 (C4 (Web Text))

Max Activating Token Index: 977

Text #2

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0950. Min Act: -0.0001

Data Index: 878540 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0917. Min Act: -0.0001

Data Index: 33511 (C4 (Web Text))

Max Activating Token Index: 396

Text #4

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0912. Min Act: -0.0001

Data Index: 678732 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0803. Min Act: -0.0001

Data Index: 587243 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0883. Min Act: -0.0001

Data Index: 881643 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0824. Min Act: -0.0001

Data Index: 600987 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0907. Min Act: -0.0001

Data Index: 1165474 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0816. Min Act: -0.0001

Data Index: 532885 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0787. Min Act: -0.0001

Data Index: 377059 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0812. Min Act: -0.0001

Data Index: 1228945 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0778. Min Act: -0.0001

Data Index: 668393 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0740. Min Act: -0.0001

Data Index: 471026 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0761. Min Act: -0.0001

Data Index: 1156286 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0783. Min Act: -0.0001

Data Index: 505242 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0836. Min Act: -0.0001

Data Index: 731365 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0808. Min Act: -0.0001

Data Index: 87793 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0788. Min Act: -0.0001

Data Index: 1203584 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0763. Min Act: -0.0001

Data Index: 1170348 (C4 (Web Text))

Max Activating Token Index: 479