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

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

Neuron 4497 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0907. Min Range: -3.0907

Max Act: 2.9514. Min Act: -0.0000

Data Index: 1153286 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 3.0907. Min Range: -3.0907

Max Act: 2.9378. Min Act: -0.0000

Data Index: 841429 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 3.0907. Min Range: -3.0907

Max Act: 2.7754. Min Act: -0.0000

Data Index: 38652 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 3.0907. Min Range: -3.0907

Max Act: 3.0907. Min Act: -0.0000

Data Index: 406097 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 3.0907. Min Range: -3.0907

Max Act: 2.8658. Min Act: -0.0000

Data Index: 1211700 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 3.0907. Min Range: -3.0907

Max Act: 3.0185. Min Act: -0.0000

Data Index: 442861 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 3.0907. Min Range: -3.0907

Max Act: 3.0616. Min Act: -0.0000

Data Index: 906337 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 3.0907. Min Range: -3.0907

Max Act: 2.5645. Min Act: -0.0000

Data Index: 1585 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 3.0907. Min Range: -3.0907

Max Act: 2.8065. Min Act: -0.0000

Data Index: 962322 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 3.0907. Min Range: -3.0907

Max Act: 2.9333. Min Act: -0.0000

Data Index: 1284783 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 3.0907. Min Range: -3.0907

Max Act: 3.0795. Min Act: -0.0000

Data Index: 1234966 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 3.0907. Min Range: -3.0907

Max Act: 2.9193. Min Act: -0.0000

Data Index: 40024 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 3.0907. Min Range: -3.0907

Max Act: 2.8912. Min Act: -0.0000

Data Index: 840196 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 3.0907. Min Range: -3.0907

Max Act: 2.9025. Min Act: -0.0000

Data Index: 226717 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 3.0907. Min Range: -3.0907

Max Act: 2.8821. Min Act: -0.0000

Data Index: 1051029 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 3.0907. Min Range: -3.0907

Max Act: 2.8785. Min Act: -0.0000

Data Index: 1215449 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 3.0907. Min Range: -3.0907

Max Act: 2.9230. Min Act: -0.0000

Data Index: 1398 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 3.0907. Min Range: -3.0907

Max Act: 2.9150. Min Act: -0.0000

Data Index: 402436 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 3.0907. Min Range: -3.0907

Max Act: 2.8598. Min Act: -0.0000

Data Index: 282077 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 3.0907. Min Range: -3.0907

Max Act: 2.5724. Min Act: -0.0000

Data Index: 505438 (C4 (Web Text))

Max Activating Token Index: 808