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

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

Neuron 3394 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: 0.7574. Min Range: -0.7574

Max Act: 0.7574. Min Act: -0.0000

Data Index: 1139991 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6942. Min Act: -0.0000

Data Index: 209268 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.5962. Min Act: -0.0000

Data Index: 162415 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.5924. Min Act: -0.0000

Data Index: 155206 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.5782. Min Act: -0.0000

Data Index: 965508 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.5929. Min Act: -0.0000

Data Index: 1199140 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.5761. Min Act: -0.0000

Data Index: 801453 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.5663. Min Act: -0.0000

Data Index: 540203 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.5427. Min Act: -0.0000

Data Index: 1040478 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.5615. Min Act: -0.0000

Data Index: 487171 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.5505. Min Act: -0.0000

Data Index: 26489 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.5595. Min Act: -0.0000

Data Index: 1150751 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.4910. Min Act: -0.0000

Data Index: 1242503 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.5197. Min Act: -0.0000

Data Index: 322295 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.5254. Min Act: -0.0000

Data Index: 807992 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.5090. Min Act: -0.0000

Data Index: 386510 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.5079. Min Act: -0.0000

Data Index: 247657 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.4679. Min Act: -0.0000

Data Index: 205072 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.5241. Min Act: -0.0000

Data Index: 932840 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.4863. Min Act: -0.0000

Data Index: 603683 (C4 (Web Text))

Max Activating Token Index: 670