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

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

Neuron 706 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.7322. Min Act: -0.0001

Data Index: 259678 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.6947. Min Act: -0.0001

Data Index: 334743 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.6957. Min Act: -0.0001

Data Index: 1071208 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.6823. Min Act: -0.0001

Data Index: 1284253 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.6680. Min Act: -0.0001

Data Index: 1324748 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.7115. Min Act: -0.0001

Data Index: 131578 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.6874. Min Act: -0.0001

Data Index: 93958 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.6842. Min Act: -0.0001

Data Index: 81352 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.6998. Min Act: -0.0001

Data Index: 1327092 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.7006. Min Act: -0.0001

Data Index: 294569 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.6452. Min Act: -0.0001

Data Index: 492677 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.6688. Min Act: -0.0001

Data Index: 745188 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.6918. Min Act: -0.0001

Data Index: 669787 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.6938. Min Act: -0.0001

Data Index: 574842 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.6058. Min Act: -0.0001

Data Index: 409373 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.7104. Min Act: -0.0001

Data Index: 379054 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.6592. Min Act: -0.0001

Data Index: 400061 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.6688. Min Act: -0.0001

Data Index: 1314131 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.6455. Min Act: -0.0001

Data Index: 937748 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.6879. Min Act: -0.0001

Data Index: 1280362 (C4 (Web Text))

Max Activating Token Index: 208