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

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

Neuron 1200 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.4894. Min Act: -0.0000

Data Index: 1347897 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 3.4894. Min Range: -3.4894

Max Act: 2.8364. Min Act: -0.0000

Data Index: 894009 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 3.4894. Min Range: -3.4894

Max Act: 2.7943. Min Act: -0.0000

Data Index: 864582 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 3.4894. Min Range: -3.4894

Max Act: 2.8721. Min Act: -0.0000

Data Index: 530077 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 3.4894. Min Range: -3.4894

Max Act: 2.6631. Min Act: -0.0000

Data Index: 505187 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 3.4894. Min Range: -3.4894

Max Act: 2.6254. Min Act: -0.0000

Data Index: 598821 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 3.4894. Min Range: -3.4894

Max Act: 2.7236. Min Act: -0.0000

Data Index: 1043616 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 3.4894. Min Range: -3.4894

Max Act: 2.6834. Min Act: -0.0000

Data Index: 167679 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 3.4894. Min Range: -3.4894

Max Act: 2.5474. Min Act: -0.0000

Data Index: 1021758 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 3.4894. Min Range: -3.4894

Max Act: 2.6249. Min Act: -0.0000

Data Index: 547581 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 3.4894. Min Range: -3.4894

Max Act: 2.3684. Min Act: -0.0000

Data Index: 294530 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 3.4894. Min Range: -3.4894

Max Act: 2.3476. Min Act: -0.0000

Data Index: 1152241 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 3.4894. Min Range: -3.4894

Max Act: 2.3177. Min Act: -0.0000

Data Index: 739509 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 3.4894. Min Range: -3.4894

Max Act: 2.2867. Min Act: -0.0000

Data Index: 616531 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 3.4894. Min Range: -3.4894

Max Act: 2.1411. Min Act: -0.0000

Data Index: 1113696 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 3.4894. Min Range: -3.4894

Max Act: 2.3924. Min Act: -0.0000

Data Index: 1115170 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 3.4894. Min Range: -3.4894

Max Act: 1.9894. Min Act: -0.0000

Data Index: 144643 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 3.4894. Min Range: -3.4894

Max Act: 2.1889. Min Act: -0.0000

Data Index: 520481 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 3.4894. Min Range: -3.4894

Max Act: 2.1784. Min Act: -0.0000

Data Index: 801150 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 3.4894. Min Range: -3.4894

Max Act: 2.1453. Min Act: -0.0000

Data Index: 128995 (C4 (Web Text))

Max Activating Token Index: 926