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

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

Neuron 2906 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.5851. Min Act: 0.0000

Data Index: 1084619 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.5254. Min Act: -0.0000

Data Index: 1286144 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.4987. Min Act: -0.0000

Data Index: 917022 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.4883. Min Act: -0.0001

Data Index: 1133193 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.4768. Min Act: -0.0000

Data Index: 685035 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.4298. Min Act: -0.0001

Data Index: 1356981 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.4110. Min Act: -0.0000

Data Index: 834184 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.4145. Min Act: -0.0000

Data Index: 484446 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.3929. Min Act: -0.0000

Data Index: 1069061 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.3830. Min Act: -0.0000

Data Index: 182266 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.3975. Min Act: -0.0001

Data Index: 833197 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.3639. Min Act: -0.0001

Data Index: 1248411 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.3652. Min Act: 0.0000

Data Index: 175276 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.3668. Min Act: -0.0001

Data Index: 1061224 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.3315. Min Act: -0.0000

Data Index: 1055217 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.3488. Min Act: -0.0001

Data Index: 165280 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.3456. Min Act: -0.0000

Data Index: 82119 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.3256. Min Act: -0.0000

Data Index: 1290099 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.3507. Min Act: -0.0000

Data Index: 420507 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.3471. Min Act: -0.0000

Data Index: 780202 (C4 (Web Text))

Max Activating Token Index: 183