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

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

Neuron 4396 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: 3.4088. Min Range: -3.4088

Max Act: 3.4088. Min Act: -0.0000

Data Index: 739136 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 3.4088. Min Range: -3.4088

Max Act: 3.1570. Min Act: -0.0000

Data Index: 917725 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 3.4088. Min Range: -3.4088

Max Act: 2.8754. Min Act: -0.0000

Data Index: 555763 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 3.4088. Min Range: -3.4088

Max Act: 3.1313. Min Act: -0.0000

Data Index: 162768 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 3.4088. Min Range: -3.4088

Max Act: 2.6905. Min Act: -0.0000

Data Index: 1181405 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 3.4088. Min Range: -3.4088

Max Act: 2.7600. Min Act: -0.0000

Data Index: 703133 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 3.4088. Min Range: -3.4088

Max Act: 2.7279. Min Act: -0.0000

Data Index: 763864 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 3.4088. Min Range: -3.4088

Max Act: 2.6654. Min Act: -0.0000

Data Index: 1213078 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 3.4088. Min Range: -3.4088

Max Act: 2.6700. Min Act: -0.0000

Data Index: 1012879 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 3.4088. Min Range: -3.4088

Max Act: 2.4672. Min Act: -0.0000

Data Index: 1215400 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 3.4088. Min Range: -3.4088

Max Act: 2.4213. Min Act: -0.0000

Data Index: 1373136 (Python Code)

Max Activating Token Index: 623

Text #11

Max Range: 3.4088. Min Range: -3.4088

Max Act: 2.4888. Min Act: -0.0000

Data Index: 1622798 (Python Code)

Max Activating Token Index: 826

Text #12

Max Range: 3.4088. Min Range: -3.4088

Max Act: 2.3292. Min Act: -0.0000

Data Index: 170727 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 3.4088. Min Range: -3.4088

Max Act: 2.3296. Min Act: -0.0000

Data Index: 1329729 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 3.4088. Min Range: -3.4088

Max Act: 2.2763. Min Act: -0.0000

Data Index: 307934 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 3.4088. Min Range: -3.4088

Max Act: 2.3925. Min Act: -0.0000

Data Index: 1091600 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 3.4088. Min Range: -3.4088

Max Act: 2.4691. Min Act: -0.0000

Data Index: 461150 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 3.4088. Min Range: -3.4088

Max Act: 2.3500. Min Act: -0.0000

Data Index: 321950 (C4 (Web Text))

Max Activating Token Index: 505

Text #18

Max Range: 3.4088. Min Range: -3.4088

Max Act: 2.4631. Min Act: -0.0000

Data Index: 1313139 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 3.4088. Min Range: -3.4088

Max Act: 2.3515. Min Act: -0.0000

Data Index: 819469 (C4 (Web Text))

Max Activating Token Index: 900