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

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

Neuron 3527 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3181. Min Range: -5.3181

Max Act: 5.3181. Min Act: -0.0000

Data Index: 1204658 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 5.3181. Min Range: -5.3181

Max Act: 5.1663. Min Act: -0.0000

Data Index: 972378 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 5.3181. Min Range: -5.3181

Max Act: 4.6725. Min Act: -0.0000

Data Index: 895657 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 5.3181. Min Range: -5.3181

Max Act: 4.7433. Min Act: -0.0000

Data Index: 668051 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 5.3181. Min Range: -5.3181

Max Act: 4.2460. Min Act: -0.0000

Data Index: 637788 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 5.3181. Min Range: -5.3181

Max Act: 4.3812. Min Act: -0.0000

Data Index: 180216 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 5.3181. Min Range: -5.3181

Max Act: 3.7903. Min Act: -0.0000

Data Index: 654244 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 5.3181. Min Range: -5.3181

Max Act: 3.9429. Min Act: -0.0000

Data Index: 1124566 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 5.3181. Min Range: -5.3181

Max Act: 4.1630. Min Act: -0.0000

Data Index: 733654 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 5.3181. Min Range: -5.3181

Max Act: 3.9811. Min Act: -0.0000

Data Index: 565240 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 5.3181. Min Range: -5.3181

Max Act: 3.7404. Min Act: -0.0000

Data Index: 385907 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 5.3181. Min Range: -5.3181

Max Act: 4.0641. Min Act: -0.0000

Data Index: 442743 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 5.3181. Min Range: -5.3181

Max Act: 3.7047. Min Act: -0.0000

Data Index: 776821 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 5.3181. Min Range: -5.3181

Max Act: 3.6835. Min Act: -0.0000

Data Index: 809762 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 5.3181. Min Range: -5.3181

Max Act: 3.7955. Min Act: -0.0000

Data Index: 80459 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 5.3181. Min Range: -5.3181

Max Act: 3.8975. Min Act: -0.0000

Data Index: 9120 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 5.3181. Min Range: -5.3181

Max Act: 3.5518. Min Act: -0.0000

Data Index: 493274 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 5.3181. Min Range: -5.3181

Max Act: 3.6487. Min Act: -0.0000

Data Index: 1167160 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 5.3181. Min Range: -5.3181

Max Act: 3.4880. Min Act: -0.0000

Data Index: 985642 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 5.3181. Min Range: -5.3181

Max Act: 3.4744. Min Act: -0.0000

Data Index: 1029997 (C4 (Web Text))

Max Activating Token Index: 9