Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2589 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2469. Min Act: -0.0000

Data Index: 824862 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2540. Min Act: -0.0001

Data Index: 1134408 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2280. Min Act: -0.0000

Data Index: 552119 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2146. Min Act: -0.0001

Data Index: 80451 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2179. Min Act: -0.0000

Data Index: 634415 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2183. Min Act: -0.0001

Data Index: 216246 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2160. Min Act: -0.0001

Data Index: 308394 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2157. Min Act: 0.0000

Data Index: 275717 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2145. Min Act: 0.0001

Data Index: 406223 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2090. Min Act: 0.0001

Data Index: 204729 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2223. Min Act: -0.0001

Data Index: 384642 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2135. Min Act: -0.0001

Data Index: 509947 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2121. Min Act: 0.0000

Data Index: 456929 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2049. Min Act: -0.0000

Data Index: 484037 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2121. Min Act: -0.0001

Data Index: 88895 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2088. Min Act: -0.0001

Data Index: 1104893 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2021. Min Act: -0.0001

Data Index: 614260 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2075. Min Act: -0.0000

Data Index: 12236 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2075. Min Act: -0.0001

Data Index: 22778 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2056. Min Act: -0.0000

Data Index: 77427 (C4 (Web Text))

Max Activating Token Index: 289