Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 460 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3751. Min Range: -1.3751

Max Act: 1.3105. Min Act: -0.0001

Data Index: 290107 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 1.3751. Min Range: -1.3751

Max Act: 1.3751. Min Act: -0.0001

Data Index: 171723 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 1.3751. Min Range: -1.3751

Max Act: 1.1562. Min Act: -0.0001

Data Index: 220181 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 1.3751. Min Range: -1.3751

Max Act: 1.1455. Min Act: -0.0002

Data Index: 1159048 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 1.3751. Min Range: -1.3751

Max Act: 1.1362. Min Act: -0.0002

Data Index: 110147 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 1.3751. Min Range: -1.3751

Max Act: 1.1946. Min Act: -0.0001

Data Index: 839910 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 1.3751. Min Range: -1.3751

Max Act: 1.0487. Min Act: -0.0002

Data Index: 1226318 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 1.3751. Min Range: -1.3751

Max Act: 1.0026. Min Act: -0.0001

Data Index: 489683 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 1.3751. Min Range: -1.3751

Max Act: 0.9451. Min Act: -0.0002

Data Index: 724463 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 1.3751. Min Range: -1.3751

Max Act: 0.9562. Min Act: -0.0001

Data Index: 699543 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 1.3751. Min Range: -1.3751

Max Act: 0.9529. Min Act: -0.0001

Data Index: 553764 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 1.3751. Min Range: -1.3751

Max Act: 0.9175. Min Act: -0.0002

Data Index: 35987 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 1.3751. Min Range: -1.3751

Max Act: 0.9388. Min Act: -0.0002

Data Index: 320611 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 1.3751. Min Range: -1.3751

Max Act: 0.9357. Min Act: -0.0001

Data Index: 935570 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 1.3751. Min Range: -1.3751

Max Act: 0.8046. Min Act: -0.0001

Data Index: 900089 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 1.3751. Min Range: -1.3751

Max Act: 0.8961. Min Act: -0.0002

Data Index: 1262274 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 1.3751. Min Range: -1.3751

Max Act: 0.9465. Min Act: -0.0001

Data Index: 705770 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 1.3751. Min Range: -1.3751

Max Act: 0.9365. Min Act: -0.0001

Data Index: 347492 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 1.3751. Min Range: -1.3751

Max Act: 0.8602. Min Act: -0.0001

Data Index: 783412 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 1.3751. Min Range: -1.3751

Max Act: 0.9245. Min Act: -0.0001

Data Index: 118746 (C4 (Web Text))

Max Activating Token Index: 875