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

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

Neuron 4399 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7265. Min Range: -2.7265

Max Act: 2.7265. Min Act: -0.0000

Data Index: 880665 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 2.7265. Min Range: -2.7265

Max Act: 2.5779. Min Act: -0.0000

Data Index: 170748 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 2.7265. Min Range: -2.7265

Max Act: 2.0295. Min Act: -0.0000

Data Index: 1257962 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 2.7265. Min Range: -2.7265

Max Act: 2.0441. Min Act: -0.0000

Data Index: 39057 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 2.7265. Min Range: -2.7265

Max Act: 2.1618. Min Act: -0.0000

Data Index: 433307 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 2.7265. Min Range: -2.7265

Max Act: 2.0719. Min Act: -0.0000

Data Index: 1389851 (Python Code)

Max Activating Token Index: 380

Text #6

Max Range: 2.7265. Min Range: -2.7265

Max Act: 2.0231. Min Act: -0.0000

Data Index: 609723 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 2.7265. Min Range: -2.7265

Max Act: 1.8317. Min Act: -0.0000

Data Index: 788384 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 2.7265. Min Range: -2.7265

Max Act: 1.8550. Min Act: -0.0000

Data Index: 623816 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 2.7265. Min Range: -2.7265

Max Act: 1.8096. Min Act: -0.0000

Data Index: 1235892 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 2.7265. Min Range: -2.7265

Max Act: 1.8039. Min Act: -0.0000

Data Index: 1165354 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 2.7265. Min Range: -2.7265

Max Act: 1.9004. Min Act: -0.0000

Data Index: 728828 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 2.7265. Min Range: -2.7265

Max Act: 1.9659. Min Act: -0.0000

Data Index: 408939 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 2.7265. Min Range: -2.7265

Max Act: 1.7695. Min Act: -0.0000

Data Index: 687792 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 2.7265. Min Range: -2.7265

Max Act: 1.8150. Min Act: -0.0000

Data Index: 1026473 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 2.7265. Min Range: -2.7265

Max Act: 1.9186. Min Act: -0.0000

Data Index: 1298919 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 2.7265. Min Range: -2.7265

Max Act: 1.9473. Min Act: -0.0000

Data Index: 883707 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 2.7265. Min Range: -2.7265

Max Act: 1.8181. Min Act: -0.0000

Data Index: 118223 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 2.7265. Min Range: -2.7265

Max Act: 1.8161. Min Act: -0.0000

Data Index: 856123 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 2.7265. Min Range: -2.7265

Max Act: 1.6292. Min Act: -0.0000

Data Index: 294611 (C4 (Web Text))

Max Activating Token Index: 620