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

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

Neuron 4323 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: 1.3168. Min Range: -1.3168

Max Act: 1.2816. Min Act: -0.0000

Data Index: 416281 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.3168. Min Act: -0.0000

Data Index: 906142 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.1677. Min Act: -0.0000

Data Index: 577240 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.2221. Min Act: -0.0000

Data Index: 497690 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.2217. Min Act: -0.0000

Data Index: 437934 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.1179. Min Act: -0.0000

Data Index: 554858 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.0321. Min Act: -0.0000

Data Index: 1071955 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.1277. Min Act: -0.0000

Data Index: 255965 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.1932. Min Act: -0.0000

Data Index: 1088585 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.0493. Min Act: -0.0000

Data Index: 60550 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 1.3168. Min Range: -1.3168

Max Act: 0.9835. Min Act: -0.0000

Data Index: 1221089 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.0426. Min Act: -0.0000

Data Index: 535588 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 1.3168. Min Range: -1.3168

Max Act: 0.9637. Min Act: -0.0000

Data Index: 1270976 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.0267. Min Act: -0.0000

Data Index: 945595 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.0133. Min Act: -0.0000

Data Index: 1330095 (C4 (Web Text))

Max Activating Token Index: 41

Text #15

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.0143. Min Act: -0.0000

Data Index: 97802 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 1.3168. Min Range: -1.3168

Max Act: 0.9965. Min Act: -0.0000

Data Index: 1073283 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 1.3168. Min Range: -1.3168

Max Act: 0.9910. Min Act: -0.0000

Data Index: 229742 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.0396. Min Act: -0.0000

Data Index: 749512 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 1.3168. Min Range: -1.3168

Max Act: 0.9717. Min Act: -0.0000

Data Index: 1229129 (C4 (Web Text))

Max Activating Token Index: 162