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

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

Neuron 1140 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2864. Min Range: -2.2864

Max Act: 2.2864. Min Act: -0.0000

Data Index: 857521 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 2.2864. Min Range: -2.2864

Max Act: 1.7065. Min Act: -0.0000

Data Index: 21447 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 2.2864. Min Range: -2.2864

Max Act: 1.7000. Min Act: -0.0000

Data Index: 393705 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 2.2864. Min Range: -2.2864

Max Act: 1.6394. Min Act: -0.0000

Data Index: 1320681 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 2.2864. Min Range: -2.2864

Max Act: 1.6579. Min Act: -0.0000

Data Index: 756019 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 2.2864. Min Range: -2.2864

Max Act: 1.6718. Min Act: -0.0000

Data Index: 59735 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 2.2864. Min Range: -2.2864

Max Act: 1.5263. Min Act: -0.0000

Data Index: 1039168 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 2.2864. Min Range: -2.2864

Max Act: 1.4921. Min Act: -0.0000

Data Index: 79729 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 2.2864. Min Range: -2.2864

Max Act: 1.4927. Min Act: -0.0000

Data Index: 463705 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 2.2864. Min Range: -2.2864

Max Act: 1.5013. Min Act: -0.0000

Data Index: 124593 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 2.2864. Min Range: -2.2864

Max Act: 1.4226. Min Act: -0.0000

Data Index: 980418 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 2.2864. Min Range: -2.2864

Max Act: 1.3587. Min Act: -0.0000

Data Index: 373586 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 2.2864. Min Range: -2.2864

Max Act: 1.3606. Min Act: -0.0000

Data Index: 953846 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 2.2864. Min Range: -2.2864

Max Act: 1.3470. Min Act: -0.0000

Data Index: 624780 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 2.2864. Min Range: -2.2864

Max Act: 1.4177. Min Act: -0.0000

Data Index: 141279 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 2.2864. Min Range: -2.2864

Max Act: 1.4088. Min Act: -0.0000

Data Index: 1582446 (Python Code)

Max Activating Token Index: 71

Text #16

Max Range: 2.2864. Min Range: -2.2864

Max Act: 1.2595. Min Act: -0.0000

Data Index: 913614 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 2.2864. Min Range: -2.2864

Max Act: 1.3393. Min Act: -0.0000

Data Index: 108540 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 2.2864. Min Range: -2.2864

Max Act: 1.2716. Min Act: -0.0000

Data Index: 321388 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 2.2864. Min Range: -2.2864

Max Act: 1.3471. Min Act: -0.0000

Data Index: 187245 (C4 (Web Text))

Max Activating Token Index: 416