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

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

Neuron 3708 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: 4.2090. Min Range: -4.2090

Max Act: 4.2090. Min Act: -0.0000

Data Index: 506996 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 4.2090. Min Range: -4.2090

Max Act: 3.4797. Min Act: -0.0000

Data Index: 1154944 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 4.2090. Min Range: -4.2090

Max Act: 3.2669. Min Act: -0.0000

Data Index: 826523 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 4.2090. Min Range: -4.2090

Max Act: 3.1535. Min Act: -0.0000

Data Index: 434305 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 4.2090. Min Range: -4.2090

Max Act: 3.1774. Min Act: -0.0000

Data Index: 206570 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 4.2090. Min Range: -4.2090

Max Act: 2.9022. Min Act: -0.0000

Data Index: 488063 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 4.2090. Min Range: -4.2090

Max Act: 2.7282. Min Act: -0.0000

Data Index: 976962 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 4.2090. Min Range: -4.2090

Max Act: 2.8097. Min Act: -0.0000

Data Index: 1202566 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 4.2090. Min Range: -4.2090

Max Act: 2.7350. Min Act: -0.0000

Data Index: 110554 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 4.2090. Min Range: -4.2090

Max Act: 2.7033. Min Act: -0.0000

Data Index: 31518 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 4.2090. Min Range: -4.2090

Max Act: 2.5465. Min Act: -0.0000

Data Index: 219995 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 4.2090. Min Range: -4.2090

Max Act: 2.6921. Min Act: -0.0000

Data Index: 503732 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 4.2090. Min Range: -4.2090

Max Act: 2.5583. Min Act: -0.0000

Data Index: 1314357 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 4.2090. Min Range: -4.2090

Max Act: 2.4120. Min Act: -0.0000

Data Index: 1153208 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 4.2090. Min Range: -4.2090

Max Act: 2.5091. Min Act: -0.0000

Data Index: 1195650 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 4.2090. Min Range: -4.2090

Max Act: 2.4831. Min Act: -0.0000

Data Index: 1356857 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 4.2090. Min Range: -4.2090

Max Act: 2.4770. Min Act: -0.0000

Data Index: 832725 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 4.2090. Min Range: -4.2090

Max Act: 2.4457. Min Act: -0.0000

Data Index: 637230 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 4.2090. Min Range: -4.2090

Max Act: 2.4312. Min Act: -0.0000

Data Index: 1237546 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 4.2090. Min Range: -4.2090

Max Act: 2.4345. Min Act: -0.0000

Data Index: 114389 (C4 (Web Text))

Max Activating Token Index: 468