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

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

Neuron 5758 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: 6.0189. Min Range: -6.0189

Max Act: 6.0189. Min Act: -0.0000

Data Index: 440988 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 6.0189. Min Range: -6.0189

Max Act: 3.5318. Min Act: -0.0000

Data Index: 1118548 (C4 (Web Text))

Max Activating Token Index: 977

Text #2

Max Range: 6.0189. Min Range: -6.0189

Max Act: 3.3824. Min Act: -0.0000

Data Index: 835996 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 6.0189. Min Range: -6.0189

Max Act: 3.2992. Min Act: -0.0000

Data Index: 168650 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 6.0189. Min Range: -6.0189

Max Act: 3.1280. Min Act: -0.0000

Data Index: 169022 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 6.0189. Min Range: -6.0189

Max Act: 3.1719. Min Act: -0.0000

Data Index: 243584 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 6.0189. Min Range: -6.0189

Max Act: 3.2882. Min Act: -0.0000

Data Index: 1020711 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 6.0189. Min Range: -6.0189

Max Act: 2.9443. Min Act: -0.0000

Data Index: 496340 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 6.0189. Min Range: -6.0189

Max Act: 3.1047. Min Act: -0.0000

Data Index: 1020831 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 6.0189. Min Range: -6.0189

Max Act: 2.6729. Min Act: -0.0000

Data Index: 1120945 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 6.0189. Min Range: -6.0189

Max Act: 3.1193. Min Act: -0.0000

Data Index: 267385 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 6.0189. Min Range: -6.0189

Max Act: 3.0987. Min Act: -0.0000

Data Index: 262596 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 6.0189. Min Range: -6.0189

Max Act: 3.0462. Min Act: -0.0000

Data Index: 117538 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 6.0189. Min Range: -6.0189

Max Act: 2.8972. Min Act: -0.0000

Data Index: 1130839 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 6.0189. Min Range: -6.0189

Max Act: 2.9891. Min Act: -0.0000

Data Index: 863364 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 6.0189. Min Range: -6.0189

Max Act: 2.8921. Min Act: -0.0000

Data Index: 63161 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 6.0189. Min Range: -6.0189

Max Act: 2.8703. Min Act: -0.0000

Data Index: 1104724 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 6.0189. Min Range: -6.0189

Max Act: 2.7919. Min Act: -0.0000

Data Index: 459799 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 6.0189. Min Range: -6.0189

Max Act: 2.8050. Min Act: -0.0000

Data Index: 632159 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 6.0189. Min Range: -6.0189

Max Act: 2.5616. Min Act: -0.0000

Data Index: 523984 (C4 (Web Text))

Max Activating Token Index: 625