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

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

Neuron 5107 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: 1.0067. Min Range: -1.0067

Max Act: 0.9808. Min Act: -0.0000

Data Index: 1262112 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 1.0067. Min Range: -1.0067

Max Act: 1.0067. Min Act: -0.0000

Data Index: 156745 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.9671. Min Act: -0.0000

Data Index: 682668 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.9269. Min Act: -0.0000

Data Index: 141541 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.9195. Min Act: -0.0000

Data Index: 856248 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8748. Min Act: -0.0000

Data Index: 345582 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.9068. Min Act: -0.0000

Data Index: 367926 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8771. Min Act: -0.0000

Data Index: 619508 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8117. Min Act: 0.0000

Data Index: 563407 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8615. Min Act: -0.0000

Data Index: 74741 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8461. Min Act: -0.0000

Data Index: 43127 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8021. Min Act: -0.0000

Data Index: 580167 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8533. Min Act: -0.0000

Data Index: 881574 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.7906. Min Act: -0.0000

Data Index: 334160 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.7643. Min Act: -0.0000

Data Index: 680940 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.7613. Min Act: -0.0000

Data Index: 455077 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.7356. Min Act: -0.0000

Data Index: 473735 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.7284. Min Act: -0.0000

Data Index: 405886 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.7229. Min Act: -0.0000

Data Index: 560043 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.7361. Min Act: -0.0000

Data Index: 54803 (C4 (Web Text))

Max Activating Token Index: 492