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

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

Neuron 3713 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: 3.2385. Min Range: -3.2385

Max Act: 3.2385. Min Act: -0.0001

Data Index: 751983 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 3.2385. Min Range: -3.2385

Max Act: 2.8133. Min Act: -0.0001

Data Index: 43182 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 3.2385. Min Range: -3.2385

Max Act: 2.7824. Min Act: -0.0001

Data Index: 1015366 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 3.2385. Min Range: -3.2385

Max Act: 2.6390. Min Act: -0.0001

Data Index: 1074387 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 3.2385. Min Range: -3.2385

Max Act: 2.7524. Min Act: -0.0001

Data Index: 240491 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 3.2385. Min Range: -3.2385

Max Act: 2.7270. Min Act: -0.0001

Data Index: 103012 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 3.2385. Min Range: -3.2385

Max Act: 2.6903. Min Act: -0.0001

Data Index: 741061 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 3.2385. Min Range: -3.2385

Max Act: 2.6778. Min Act: -0.0001

Data Index: 616175 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 3.2385. Min Range: -3.2385

Max Act: 2.8137. Min Act: -0.0001

Data Index: 41595 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 3.2385. Min Range: -3.2385

Max Act: 2.6000. Min Act: -0.0001

Data Index: 657896 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 3.2385. Min Range: -3.2385

Max Act: 2.6896. Min Act: -0.0001

Data Index: 983477 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 3.2385. Min Range: -3.2385

Max Act: 2.4074. Min Act: -0.0001

Data Index: 425147 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 3.2385. Min Range: -3.2385

Max Act: 2.8804. Min Act: -0.0001

Data Index: 1200637 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 3.2385. Min Range: -3.2385

Max Act: 2.4927. Min Act: -0.0001

Data Index: 653785 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 3.2385. Min Range: -3.2385

Max Act: 2.6224. Min Act: -0.0001

Data Index: 737720 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 3.2385. Min Range: -3.2385

Max Act: 2.5037. Min Act: -0.0001

Data Index: 194880 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 3.2385. Min Range: -3.2385

Max Act: 2.3514. Min Act: -0.0001

Data Index: 1113652 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 3.2385. Min Range: -3.2385

Max Act: 2.4191. Min Act: -0.0001

Data Index: 106915 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 3.2385. Min Range: -3.2385

Max Act: 2.3824. Min Act: -0.0001

Data Index: 1198741 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 3.2385. Min Range: -3.2385

Max Act: 2.3436. Min Act: -0.0001

Data Index: 770622 (C4 (Web Text))

Max Activating Token Index: 102