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

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

Neuron 2143 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4194. Min Range: -0.4194

Max Act: 0.4194. Min Act: -0.0000

Data Index: 414923 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 0.4194. Min Range: -0.4194

Max Act: 0.3994. Min Act: -0.0000

Data Index: 1288650 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 0.4194. Min Range: -0.4194

Max Act: 0.4010. Min Act: -0.0000

Data Index: 956279 (C4 (Web Text))

Max Activating Token Index: 550

Text #3

Max Range: 0.4194. Min Range: -0.4194

Max Act: 0.3576. Min Act: -0.0000

Data Index: 438405 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 0.4194. Min Range: -0.4194

Max Act: 0.3508. Min Act: 0.0000

Data Index: 1342858 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.4194. Min Range: -0.4194

Max Act: 0.3331. Min Act: -0.0000

Data Index: 997929 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 0.4194. Min Range: -0.4194

Max Act: 0.3515. Min Act: -0.0000

Data Index: 1466090 (Python Code)

Max Activating Token Index: 506

Text #7

Max Range: 0.4194. Min Range: -0.4194

Max Act: 0.3129. Min Act: -0.0000

Data Index: 1048472 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 0.4194. Min Range: -0.4194

Max Act: 0.3226. Min Act: -0.0000

Data Index: 1654138 (Python Code)

Max Activating Token Index: 554

Text #9

Max Range: 0.4194. Min Range: -0.4194

Max Act: 0.3308. Min Act: -0.0000

Data Index: 720882 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 0.4194. Min Range: -0.4194

Max Act: 0.3229. Min Act: -0.0000

Data Index: 350864 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 0.4194. Min Range: -0.4194

Max Act: 0.3219. Min Act: -0.0000

Data Index: 682288 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 0.4194. Min Range: -0.4194

Max Act: 0.3190. Min Act: -0.0000

Data Index: 1093581 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 0.4194. Min Range: -0.4194

Max Act: 0.3009. Min Act: -0.0000

Data Index: 1367820 (Python Code)

Max Activating Token Index: 96

Text #14

Max Range: 0.4194. Min Range: -0.4194

Max Act: 0.2964. Min Act: -0.0000

Data Index: 862958 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 0.4194. Min Range: -0.4194

Max Act: 0.2990. Min Act: -0.0000

Data Index: 194828 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 0.4194. Min Range: -0.4194

Max Act: 0.2872. Min Act: -0.0000

Data Index: 1269941 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 0.4194. Min Range: -0.4194

Max Act: 0.2856. Min Act: -0.0000

Data Index: 1375348 (Python Code)

Max Activating Token Index: 959

Text #18

Max Range: 0.4194. Min Range: -0.4194

Max Act: 0.3022. Min Act: -0.0000

Data Index: 1603061 (Python Code)

Max Activating Token Index: 738

Text #19

Max Range: 0.4194. Min Range: -0.4194

Max Act: 0.3017. Min Act: -0.0000

Data Index: 1160724 (C4 (Web Text))

Max Activating Token Index: 429