Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2153 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.6185. Min Act: -0.0000

Data Index: 502793 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.5815. Min Act: -0.0001

Data Index: 1581114 (Python Code)

Max Activating Token Index: 455

Text #2

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.5221. Min Act: -0.0001

Data Index: 497972 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.5176. Min Act: -0.0001

Data Index: 1625146 (Python Code)

Max Activating Token Index: 496

Text #4

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.5066. Min Act: -0.0001

Data Index: 1633739 (Python Code)

Max Activating Token Index: 215

Text #5

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.4950. Min Act: -0.0000

Data Index: 1178727 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.4925. Min Act: -0.0000

Data Index: 1005491 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.5012. Min Act: -0.0001

Data Index: 151090 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.4642. Min Act: -0.0000

Data Index: 1344761 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.4155. Min Act: -0.0000

Data Index: 673481 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.4453. Min Act: -0.0000

Data Index: 543651 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.4408. Min Act: -0.0000

Data Index: 668833 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.4328. Min Act: -0.0000

Data Index: 452125 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.4400. Min Act: -0.0000

Data Index: 737329 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.4314. Min Act: -0.0000

Data Index: 710959 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.4180. Min Act: -0.0001

Data Index: 1510983 (Python Code)

Max Activating Token Index: 589

Text #16

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.4153. Min Act: -0.0000

Data Index: 480930 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.4002. Min Act: -0.0001

Data Index: 1577307 (Python Code)

Max Activating Token Index: 21

Text #18

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.4133. Min Act: -0.0000

Data Index: 751543 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.3937. Min Act: -0.0001

Data Index: 1566231 (Python Code)

Max Activating Token Index: 39