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

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

Neuron 453 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4424. Min Range: -1.4424

Max Act: 1.4424. Min Act: -0.0001

Data Index: 1592360 (Python Code)

Max Activating Token Index: 437

Text #1

Max Range: 1.4424. Min Range: -1.4424

Max Act: 1.2743. Min Act: -0.0001

Data Index: 1503903 (Python Code)

Max Activating Token Index: 147

Text #2

Max Range: 1.4424. Min Range: -1.4424

Max Act: 1.1345. Min Act: -0.0001

Data Index: 1405961 (Python Code)

Max Activating Token Index: 967

Text #3

Max Range: 1.4424. Min Range: -1.4424

Max Act: 1.1666. Min Act: -0.0001

Data Index: 1330365 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 1.4424. Min Range: -1.4424

Max Act: 0.9964. Min Act: -0.0001

Data Index: 1160203 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 1.4424. Min Range: -1.4424

Max Act: 1.1874. Min Act: -0.0001

Data Index: 1423742 (Python Code)

Max Activating Token Index: 744

Text #6

Max Range: 1.4424. Min Range: -1.4424

Max Act: 0.9985. Min Act: -0.0001

Data Index: 1480522 (Python Code)

Max Activating Token Index: 262

Text #7

Max Range: 1.4424. Min Range: -1.4424

Max Act: 0.9738. Min Act: -0.0001

Data Index: 154492 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 1.4424. Min Range: -1.4424

Max Act: 0.9531. Min Act: -0.0001

Data Index: 494161 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 1.4424. Min Range: -1.4424

Max Act: 0.9428. Min Act: -0.0001

Data Index: 744900 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 1.4424. Min Range: -1.4424

Max Act: 0.9496. Min Act: -0.0001

Data Index: 1095257 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 1.4424. Min Range: -1.4424

Max Act: 0.9363. Min Act: -0.0001

Data Index: 716980 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 1.4424. Min Range: -1.4424

Max Act: 0.8920. Min Act: -0.0001

Data Index: 143461 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 1.4424. Min Range: -1.4424

Max Act: 0.8754. Min Act: -0.0001

Data Index: 313190 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 1.4424. Min Range: -1.4424

Max Act: 0.8234. Min Act: -0.0001

Data Index: 544956 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 1.4424. Min Range: -1.4424

Max Act: 0.9569. Min Act: -0.0001

Data Index: 181650 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 1.4424. Min Range: -1.4424

Max Act: 1.0399. Min Act: -0.0001

Data Index: 24339 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 1.4424. Min Range: -1.4424

Max Act: 0.8651. Min Act: -0.0001

Data Index: 1302145 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 1.4424. Min Range: -1.4424

Max Act: 0.8401. Min Act: -0.0001

Data Index: 1325543 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 1.4424. Min Range: -1.4424

Max Act: 0.8801. Min Act: -0.0001

Data Index: 228894 (C4 (Web Text))

Max Activating Token Index: 501