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

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

Neuron 3115 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2540. Min Act: -0.0001

Data Index: 603407 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2384. Min Act: -0.0001

Data Index: 872235 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2430. Min Act: -0.0001

Data Index: 1308132 (C4 (Web Text))

Max Activating Token Index: 623

Text #3

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2431. Min Act: -0.0001

Data Index: 908588 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2595. Min Act: -0.0001

Data Index: 426725 (C4 (Web Text))

Max Activating Token Index: 989

Text #5

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2170. Min Act: -0.0001

Data Index: 1273780 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2504. Min Act: -0.0001

Data Index: 156240 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2483. Min Act: -0.0001

Data Index: 233118 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2328. Min Act: -0.0001

Data Index: 379180 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2349. Min Act: -0.0001

Data Index: 474282 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2238. Min Act: -0.0001

Data Index: 902557 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2164. Min Act: -0.0001

Data Index: 1149363 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2163. Min Act: -0.0001

Data Index: 517121 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.1965. Min Act: -0.0001

Data Index: 1233132 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2117. Min Act: -0.0001

Data Index: 1279123 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2080. Min Act: -0.0001

Data Index: 344411 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2105. Min Act: -0.0001

Data Index: 42031 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.1958. Min Act: -0.0001

Data Index: 1248276 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.1999. Min Act: -0.0001

Data Index: 924964 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2046. Min Act: -0.0001

Data Index: 435100 (C4 (Web Text))

Max Activating Token Index: 350