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

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

Neuron 1402 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3693. Min Act: -0.0004

Data Index: 1567843 (Python Code)

Max Activating Token Index: 969

Text #1

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3111. Min Act: -0.0004

Data Index: 1371791 (Python Code)

Max Activating Token Index: 290

Text #2

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3203. Min Act: -0.0004

Data Index: 1386400 (Python Code)

Max Activating Token Index: 191

Text #3

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3237. Min Act: -0.0004

Data Index: 1589504 (Python Code)

Max Activating Token Index: 279

Text #4

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3080. Min Act: -0.0004

Data Index: 1652410 (Python Code)

Max Activating Token Index: 287

Text #5

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3160. Min Act: -0.0004

Data Index: 1510888 (Python Code)

Max Activating Token Index: 50

Text #6

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3049. Min Act: -0.0004

Data Index: 1501417 (Python Code)

Max Activating Token Index: 54

Text #7

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.2842. Min Act: -0.0004

Data Index: 1593821 (Python Code)

Max Activating Token Index: 318

Text #8

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3002. Min Act: -0.0004

Data Index: 1449621 (Python Code)

Max Activating Token Index: 284

Text #9

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3079. Min Act: -0.0004

Data Index: 1360657 (Python Code)

Max Activating Token Index: 16

Text #10

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.2964. Min Act: -0.0004

Data Index: 1615147 (Python Code)

Max Activating Token Index: 146

Text #11

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3060. Min Act: -0.0004

Data Index: 1391556 (Python Code)

Max Activating Token Index: 235

Text #12

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3062. Min Act: -0.0004

Data Index: 1552604 (Python Code)

Max Activating Token Index: 205

Text #13

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.2919. Min Act: -0.0004

Data Index: 1627500 (Python Code)

Max Activating Token Index: 325

Text #14

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.2860. Min Act: -0.0004

Data Index: 1529582 (Python Code)

Max Activating Token Index: 95

Text #15

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.2962. Min Act: -0.0004

Data Index: 1573265 (Python Code)

Max Activating Token Index: 260

Text #16

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.2936. Min Act: -0.0004

Data Index: 1577542 (Python Code)

Max Activating Token Index: 164

Text #17

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3010. Min Act: -0.0004

Data Index: 1656133 (Python Code)

Max Activating Token Index: 261

Text #18

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.2934. Min Act: -0.0004

Data Index: 1643594 (Python Code)

Max Activating Token Index: 328

Text #19

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.2923. Min Act: -0.0004

Data Index: 1509725 (Python Code)

Max Activating Token Index: 921