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

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

Neuron 2639 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6963. Min Range: -0.6963

Max Act: 0.6963. Min Act: -0.0000

Data Index: 247690 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 0.6963. Min Range: -0.6963

Max Act: 0.5763. Min Act: -0.0000

Data Index: 1120186 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 0.6963. Min Range: -0.6963

Max Act: 0.5688. Min Act: -0.0000

Data Index: 744218 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 0.6963. Min Range: -0.6963

Max Act: 0.5124. Min Act: -0.0000

Data Index: 481340 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 0.6963. Min Range: -0.6963

Max Act: 0.5016. Min Act: -0.0000

Data Index: 740204 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 0.6963. Min Range: -0.6963

Max Act: 0.4622. Min Act: -0.0000

Data Index: 1140811 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 0.6963. Min Range: -0.6963

Max Act: 0.4705. Min Act: -0.0000

Data Index: 25208 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.6963. Min Range: -0.6963

Max Act: 0.4450. Min Act: -0.0000

Data Index: 684692 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 0.6963. Min Range: -0.6963

Max Act: 0.4412. Min Act: -0.0000

Data Index: 613157 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 0.6963. Min Range: -0.6963

Max Act: 0.4447. Min Act: -0.0000

Data Index: 481248 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 0.6963. Min Range: -0.6963

Max Act: 0.4417. Min Act: -0.0000

Data Index: 629816 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 0.6963. Min Range: -0.6963

Max Act: 0.4392. Min Act: -0.0000

Data Index: 448906 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 0.6963. Min Range: -0.6963

Max Act: 0.4161. Min Act: -0.0000

Data Index: 339430 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 0.6963. Min Range: -0.6963

Max Act: 0.4222. Min Act: 0.0000

Data Index: 1305823 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 0.6963. Min Range: -0.6963

Max Act: 0.3969. Min Act: -0.0000

Data Index: 613423 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 0.6963. Min Range: -0.6963

Max Act: 0.4012. Min Act: -0.0000

Data Index: 463710 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 0.6963. Min Range: -0.6963

Max Act: 0.4020. Min Act: -0.0000

Data Index: 665838 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 0.6963. Min Range: -0.6963

Max Act: 0.4061. Min Act: -0.0000

Data Index: 565441 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.6963. Min Range: -0.6963

Max Act: 0.3958. Min Act: -0.0000

Data Index: 1078920 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 0.6963. Min Range: -0.6963

Max Act: 0.4036. Min Act: -0.0000

Data Index: 662533 (C4 (Web Text))

Max Activating Token Index: 403