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

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

Neuron 3046 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4154. Min Range: -2.4154

Max Act: 2.4154. Min Act: -0.0000

Data Index: 886520 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 2.4154. Min Range: -2.4154

Max Act: 2.3233. Min Act: -0.0000

Data Index: 77393 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 2.4154. Min Range: -2.4154

Max Act: 2.2940. Min Act: -0.0000

Data Index: 331608 (C4 (Web Text))

Max Activating Token Index: 960

Text #3

Max Range: 2.4154. Min Range: -2.4154

Max Act: 2.2465. Min Act: -0.0000

Data Index: 1519699 (Python Code)

Max Activating Token Index: 502

Text #4

Max Range: 2.4154. Min Range: -2.4154

Max Act: 2.3775. Min Act: -0.0000

Data Index: 950735 (C4 (Web Text))

Max Activating Token Index: 939

Text #5

Max Range: 2.4154. Min Range: -2.4154

Max Act: 2.0428. Min Act: -0.0000

Data Index: 229821 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 2.4154. Min Range: -2.4154

Max Act: 2.1538. Min Act: -0.0000

Data Index: 696584 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 2.4154. Min Range: -2.4154

Max Act: 2.0502. Min Act: -0.0000

Data Index: 1595955 (Python Code)

Max Activating Token Index: 290

Text #8

Max Range: 2.4154. Min Range: -2.4154

Max Act: 2.1090. Min Act: -0.0000

Data Index: 77790 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 2.4154. Min Range: -2.4154

Max Act: 1.7475. Min Act: -0.0000

Data Index: 5395 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 2.4154. Min Range: -2.4154

Max Act: 2.0865. Min Act: -0.0000

Data Index: 445170 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 2.4154. Min Range: -2.4154

Max Act: 2.0476. Min Act: -0.0000

Data Index: 1236697 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 2.4154. Min Range: -2.4154

Max Act: 2.1357. Min Act: -0.0000

Data Index: 18668 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 2.4154. Min Range: -2.4154

Max Act: 2.1067. Min Act: -0.0000

Data Index: 849469 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 2.4154. Min Range: -2.4154

Max Act: 1.7623. Min Act: -0.0000

Data Index: 1405897 (Python Code)

Max Activating Token Index: 142

Text #15

Max Range: 2.4154. Min Range: -2.4154

Max Act: 1.8410. Min Act: -0.0000

Data Index: 25261 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 2.4154. Min Range: -2.4154

Max Act: 1.8304. Min Act: -0.0000

Data Index: 1586935 (Python Code)

Max Activating Token Index: 207

Text #17

Max Range: 2.4154. Min Range: -2.4154

Max Act: 1.7214. Min Act: -0.0000

Data Index: 1472658 (Python Code)

Max Activating Token Index: 305

Text #18

Max Range: 2.4154. Min Range: -2.4154

Max Act: 1.8697. Min Act: -0.0000

Data Index: 561047 (C4 (Web Text))

Max Activating Token Index: 441

Text #19

Max Range: 2.4154. Min Range: -2.4154

Max Act: 1.8681. Min Act: -0.0000

Data Index: 1604683 (Python Code)

Max Activating Token Index: 29