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

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

Neuron 1306 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2341. Min Range: -1.2341

Max Act: 1.0198. Min Act: -0.0003

Data Index: 585873 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 1.2341. Min Range: -1.2341

Max Act: 1.0453. Min Act: -0.0003

Data Index: 829542 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 1.2341. Min Range: -1.2341

Max Act: 1.0741. Min Act: -0.0003

Data Index: 370998 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 1.2341. Min Range: -1.2341

Max Act: 1.2341. Min Act: -0.0003

Data Index: 1040532 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 1.2341. Min Range: -1.2341

Max Act: 1.0864. Min Act: -0.0003

Data Index: 220908 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 1.2341. Min Range: -1.2341

Max Act: 1.0127. Min Act: -0.0003

Data Index: 321405 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 1.2341. Min Range: -1.2341

Max Act: 0.8948. Min Act: -0.0003

Data Index: 1561494 (Python Code)

Max Activating Token Index: 278

Text #7

Max Range: 1.2341. Min Range: -1.2341

Max Act: 1.0171. Min Act: -0.0003

Data Index: 1095460 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 1.2341. Min Range: -1.2341

Max Act: 1.0918. Min Act: -0.0004

Data Index: 1513342 (Python Code)

Max Activating Token Index: 211

Text #9

Max Range: 1.2341. Min Range: -1.2341

Max Act: 0.9972. Min Act: -0.0003

Data Index: 1378868 (Python Code)

Max Activating Token Index: 349

Text #10

Max Range: 1.2341. Min Range: -1.2341

Max Act: 0.9964. Min Act: -0.0003

Data Index: 1410645 (Python Code)

Max Activating Token Index: 373

Text #11

Max Range: 1.2341. Min Range: -1.2341

Max Act: 1.0262. Min Act: -0.0003

Data Index: 1227158 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 1.2341. Min Range: -1.2341

Max Act: 0.8093. Min Act: -0.0003

Data Index: 492197 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 1.2341. Min Range: -1.2341

Max Act: 0.9841. Min Act: -0.0003

Data Index: 102744 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 1.2341. Min Range: -1.2341

Max Act: 0.9545. Min Act: -0.0003

Data Index: 1503231 (Python Code)

Max Activating Token Index: 295

Text #15

Max Range: 1.2341. Min Range: -1.2341

Max Act: 1.0569. Min Act: -0.0003

Data Index: 1554368 (Python Code)

Max Activating Token Index: 297

Text #16

Max Range: 1.2341. Min Range: -1.2341

Max Act: 0.9800. Min Act: -0.0003

Data Index: 186667 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 1.2341. Min Range: -1.2341

Max Act: 1.0538. Min Act: -0.0003

Data Index: 292233 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 1.2341. Min Range: -1.2341

Max Act: 1.0833. Min Act: -0.0003

Data Index: 86371 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 1.2341. Min Range: -1.2341

Max Act: 0.9922. Min Act: -0.0003

Data Index: 1351154 (C4 (Web Text))

Max Activating Token Index: 178