Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 368 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0158. Min Range: -1.0158

Max Act: 1.0124. Min Act: -0.0001

Data Index: 221274 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 1.0158. Min Range: -1.0158

Max Act: 1.0158. Min Act: -0.0001

Data Index: 819199 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 1.0158. Min Range: -1.0158

Max Act: 1.0028. Min Act: -0.0001

Data Index: 226454 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.9120. Min Act: -0.0001

Data Index: 1137161 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.9512. Min Act: -0.0000

Data Index: 945763 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.8981. Min Act: -0.0001

Data Index: 1081929 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.8683. Min Act: -0.0001

Data Index: 1024306 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.8683. Min Act: -0.0001

Data Index: 866280 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.8356. Min Act: -0.0001

Data Index: 295324 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.8916. Min Act: -0.0001

Data Index: 731010 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.9143. Min Act: -0.0001

Data Index: 1270173 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.8664. Min Act: -0.0001

Data Index: 957174 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.8668. Min Act: -0.0001

Data Index: 1137745 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.8677. Min Act: -0.0001

Data Index: 1325578 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.7910. Min Act: -0.0001

Data Index: 287427 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.8113. Min Act: -0.0001

Data Index: 496931 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.7995. Min Act: -0.0001

Data Index: 218755 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.8190. Min Act: -0.0001

Data Index: 436710 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.8261. Min Act: -0.0001

Data Index: 344971 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.7407. Min Act: -0.0001

Data Index: 365736 (C4 (Web Text))

Max Activating Token Index: 681