Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1854 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.2674. Min Act: -0.0001

Data Index: 1228686 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.2717. Min Act: -0.0001

Data Index: 21702 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.2226. Min Act: -0.0000

Data Index: 1049079 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.2284. Min Act: -0.0000

Data Index: 1217870 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.2239. Min Act: -0.0000

Data Index: 223864 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.2250. Min Act: -0.0001

Data Index: 1157241 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.2083. Min Act: -0.0000

Data Index: 343350 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.2090. Min Act: -0.0001

Data Index: 481796 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.2079. Min Act: -0.0001

Data Index: 829715 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.2297. Min Act: -0.0000

Data Index: 929002 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.2140. Min Act: -0.0000

Data Index: 1197089 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.1975. Min Act: -0.0001

Data Index: 323283 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.2028. Min Act: -0.0000

Data Index: 206415 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.2089. Min Act: -0.0001

Data Index: 491796 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.2214. Min Act: -0.0000

Data Index: 62296 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.2061. Min Act: -0.0000

Data Index: 166713 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.1979. Min Act: -0.0000

Data Index: 946807 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.1987. Min Act: -0.0000

Data Index: 504028 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.1846. Min Act: -0.0001

Data Index: 1133395 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 0.2717. Min Range: -0.2717

Max Act: 0.2065. Min Act: -0.0000

Data Index: 610580 (C4 (Web Text))

Max Activating Token Index: 991