Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2586 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1181. Min Range: -1.1181

Max Act: 1.1181. Min Act: -0.0000

Data Index: 574158 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 1.1181. Min Range: -1.1181

Max Act: 0.9850. Min Act: -0.0000

Data Index: 497480 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 1.1181. Min Range: -1.1181

Max Act: 0.9283. Min Act: -0.0000

Data Index: 1616542 (Python Code)

Max Activating Token Index: 435

Text #3

Max Range: 1.1181. Min Range: -1.1181

Max Act: 0.8418. Min Act: -0.0000

Data Index: 182021 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 1.1181. Min Range: -1.1181

Max Act: 0.8073. Min Act: -0.0000

Data Index: 227808 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 1.1181. Min Range: -1.1181

Max Act: 0.7240. Min Act: -0.0000

Data Index: 1440325 (Python Code)

Max Activating Token Index: 726

Text #6

Max Range: 1.1181. Min Range: -1.1181

Max Act: 0.7216. Min Act: -0.0000

Data Index: 1485998 (Python Code)

Max Activating Token Index: 221

Text #7

Max Range: 1.1181. Min Range: -1.1181

Max Act: 0.7337. Min Act: -0.0000

Data Index: 1646563 (Python Code)

Max Activating Token Index: 325

Text #8

Max Range: 1.1181. Min Range: -1.1181

Max Act: 0.7319. Min Act: -0.0000

Data Index: 1488704 (Python Code)

Max Activating Token Index: 177

Text #9

Max Range: 1.1181. Min Range: -1.1181

Max Act: 0.6602. Min Act: -0.0000

Data Index: 157578 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 1.1181. Min Range: -1.1181

Max Act: 0.6482. Min Act: -0.0000

Data Index: 368881 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 1.1181. Min Range: -1.1181

Max Act: 0.6752. Min Act: -0.0000

Data Index: 1624786 (Python Code)

Max Activating Token Index: 1004

Text #12

Max Range: 1.1181. Min Range: -1.1181

Max Act: 0.5675. Min Act: -0.0000

Data Index: 896855 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 1.1181. Min Range: -1.1181

Max Act: 0.6766. Min Act: -0.0000

Data Index: 1516385 (Python Code)

Max Activating Token Index: 485

Text #14

Max Range: 1.1181. Min Range: -1.1181

Max Act: 0.6974. Min Act: -0.0000

Data Index: 1391068 (Python Code)

Max Activating Token Index: 40

Text #15

Max Range: 1.1181. Min Range: -1.1181

Max Act: 0.6386. Min Act: -0.0000

Data Index: 1595135 (Python Code)

Max Activating Token Index: 146

Text #16

Max Range: 1.1181. Min Range: -1.1181

Max Act: 0.6059. Min Act: -0.0000

Data Index: 734644 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 1.1181. Min Range: -1.1181

Max Act: 0.6032. Min Act: -0.0000

Data Index: 1466687 (Python Code)

Max Activating Token Index: 359

Text #18

Max Range: 1.1181. Min Range: -1.1181

Max Act: 0.5667. Min Act: -0.0000

Data Index: 1625770 (Python Code)

Max Activating Token Index: 478

Text #19

Max Range: 1.1181. Min Range: -1.1181

Max Act: 0.5704. Min Act: -0.0000

Data Index: 1400450 (Python Code)

Max Activating Token Index: 649