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

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

Neuron 3050 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.7129. Min Act: -0.0001

Data Index: 37358 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.7096. Min Act: -0.0001

Data Index: 1013208 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.5932. Min Act: -0.0001

Data Index: 50094 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.5786. Min Act: -0.0001

Data Index: 447875 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.5601. Min Act: -0.0001

Data Index: 375197 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.5677. Min Act: -0.0001

Data Index: 744975 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.5452. Min Act: -0.0001

Data Index: 861764 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.5241. Min Act: -0.0001

Data Index: 354241 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.5283. Min Act: -0.0001

Data Index: 1350486 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.5600. Min Act: -0.0001

Data Index: 553437 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.5208. Min Act: -0.0001

Data Index: 778302 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.5328. Min Act: -0.0001

Data Index: 324187 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.5512. Min Act: -0.0001

Data Index: 13570 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.5058. Min Act: -0.0001

Data Index: 619575 (C4 (Web Text))

Max Activating Token Index: 563

Text #14

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.5204. Min Act: -0.0001

Data Index: 896917 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.5132. Min Act: -0.0001

Data Index: 504726 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.4728. Min Act: -0.0001

Data Index: 119106 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.4905. Min Act: -0.0001

Data Index: 1262339 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.4798. Min Act: -0.0001

Data Index: 1319792 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.5150. Min Act: -0.0001

Data Index: 1273075 (C4 (Web Text))

Max Activating Token Index: 862