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

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

Neuron 2331 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.5944. Min Act: 0.0000

Data Index: 214885 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.5757. Min Act: 0.0000

Data Index: 45870 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4978. Min Act: -0.0000

Data Index: 779176 (C4 (Web Text))

Max Activating Token Index: 903

Text #3

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.5206. Min Act: -0.0000

Data Index: 1068054 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.5055. Min Act: -0.0000

Data Index: 88877 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4858. Min Act: -0.0000

Data Index: 996694 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.5015. Min Act: 0.0000

Data Index: 311156 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4946. Min Act: -0.0000

Data Index: 163741 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4767. Min Act: -0.0000

Data Index: 505896 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4527. Min Act: -0.0000

Data Index: 770253 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4537. Min Act: -0.0000

Data Index: 1110016 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4295. Min Act: -0.0000

Data Index: 106991 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4449. Min Act: -0.0000

Data Index: 805494 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4584. Min Act: -0.0000

Data Index: 520214 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4168. Min Act: -0.0000

Data Index: 623470 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4196. Min Act: -0.0000

Data Index: 839880 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4266. Min Act: -0.0000

Data Index: 66680 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4149. Min Act: -0.0000

Data Index: 774667 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4403. Min Act: -0.0000

Data Index: 354514 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4263. Min Act: 0.0002

Data Index: 581247 (C4 (Web Text))

Max Activating Token Index: 765