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

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

Neuron 4743 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1439. Min Range: -5.1439

Max Act: 5.1439. Min Act: -0.0000

Data Index: 902161 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 5.1439. Min Range: -5.1439

Max Act: 5.1042. Min Act: -0.0000

Data Index: 784050 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 5.1439. Min Range: -5.1439

Max Act: 4.4475. Min Act: -0.0000

Data Index: 1047889 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 5.1439. Min Range: -5.1439

Max Act: 4.7953. Min Act: -0.0000

Data Index: 1058117 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 5.1439. Min Range: -5.1439

Max Act: 4.7746. Min Act: -0.0000

Data Index: 811035 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 5.1439. Min Range: -5.1439

Max Act: 4.7641. Min Act: -0.0000

Data Index: 796222 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 5.1439. Min Range: -5.1439

Max Act: 4.1633. Min Act: -0.0000

Data Index: 821624 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 5.1439. Min Range: -5.1439

Max Act: 4.6132. Min Act: -0.0000

Data Index: 1247368 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 5.1439. Min Range: -5.1439

Max Act: 4.2524. Min Act: -0.0000

Data Index: 264986 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 5.1439. Min Range: -5.1439

Max Act: 3.8896. Min Act: -0.0000

Data Index: 720512 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 5.1439. Min Range: -5.1439

Max Act: 4.3003. Min Act: -0.0001

Data Index: 39830 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 5.1439. Min Range: -5.1439

Max Act: 4.2882. Min Act: -0.0000

Data Index: 1209889 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 5.1439. Min Range: -5.1439

Max Act: 4.2651. Min Act: -0.0000

Data Index: 631347 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 5.1439. Min Range: -5.1439

Max Act: 4.4263. Min Act: -0.0000

Data Index: 1184603 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 5.1439. Min Range: -5.1439

Max Act: 4.0438. Min Act: -0.0000

Data Index: 1059798 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 5.1439. Min Range: -5.1439

Max Act: 4.2153. Min Act: -0.0000

Data Index: 20075 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 5.1439. Min Range: -5.1439

Max Act: 4.1545. Min Act: -0.0000

Data Index: 991703 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 5.1439. Min Range: -5.1439

Max Act: 4.3338. Min Act: -0.0000

Data Index: 402918 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 5.1439. Min Range: -5.1439

Max Act: 4.1387. Min Act: -0.0000

Data Index: 685690 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 5.1439. Min Range: -5.1439

Max Act: 4.2330. Min Act: -0.0001

Data Index: 864643 (C4 (Web Text))

Max Activating Token Index: 289