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

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

Neuron 3190 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3369. Min Range: -1.3369

Max Act: 1.3369. Min Act: -0.0000

Data Index: 8486 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 1.3369. Min Range: -1.3369

Max Act: 1.2117. Min Act: -0.0000

Data Index: 635394 (C4 (Web Text))

Max Activating Token Index: 501

Text #2

Max Range: 1.3369. Min Range: -1.3369

Max Act: 1.0482. Min Act: -0.0000

Data Index: 1281950 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 1.3369. Min Range: -1.3369

Max Act: 0.9403. Min Act: -0.0000

Data Index: 1356816 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 1.3369. Min Range: -1.3369

Max Act: 0.9736. Min Act: -0.0000

Data Index: 1125814 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 1.3369. Min Range: -1.3369

Max Act: 1.0293. Min Act: -0.0000

Data Index: 168419 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 1.3369. Min Range: -1.3369

Max Act: 0.9717. Min Act: -0.0000

Data Index: 37262 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 1.3369. Min Range: -1.3369

Max Act: 0.8999. Min Act: -0.0000

Data Index: 1077552 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 1.3369. Min Range: -1.3369

Max Act: 0.9351. Min Act: -0.0000

Data Index: 374918 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 1.3369. Min Range: -1.3369

Max Act: 0.9187. Min Act: -0.0000

Data Index: 1161057 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 1.3369. Min Range: -1.3369

Max Act: 0.8919. Min Act: -0.0000

Data Index: 960812 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 1.3369. Min Range: -1.3369

Max Act: 0.8614. Min Act: -0.0000

Data Index: 1332925 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 1.3369. Min Range: -1.3369

Max Act: 0.9630. Min Act: -0.0000

Data Index: 261153 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 1.3369. Min Range: -1.3369

Max Act: 0.8379. Min Act: -0.0000

Data Index: 1042677 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 1.3369. Min Range: -1.3369

Max Act: 0.8970. Min Act: -0.0000

Data Index: 100683 (C4 (Web Text))

Max Activating Token Index: 237

Text #15

Max Range: 1.3369. Min Range: -1.3369

Max Act: 0.8531. Min Act: -0.0000

Data Index: 636161 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 1.3369. Min Range: -1.3369

Max Act: 0.8282. Min Act: -0.0000

Data Index: 888584 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 1.3369. Min Range: -1.3369

Max Act: 0.8746. Min Act: -0.0000

Data Index: 442168 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 1.3369. Min Range: -1.3369

Max Act: 0.8957. Min Act: -0.0000

Data Index: 1272597 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 1.3369. Min Range: -1.3369

Max Act: 0.8758. Min Act: -0.0000

Data Index: 675622 (C4 (Web Text))

Max Activating Token Index: 661