Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2470 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2118. Min Act: -0.0001

Data Index: 1245705 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2097. Min Act: -0.0001

Data Index: 877355 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2493. Min Act: -0.0001

Data Index: 1192673 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1998. Min Act: -0.0001

Data Index: 473452 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2050. Min Act: -0.0001

Data Index: 821133 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2050. Min Act: -0.0001

Data Index: 440887 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1927. Min Act: -0.0001

Data Index: 543801 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1964. Min Act: -0.0001

Data Index: 516970 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1768. Min Act: -0.0001

Data Index: 473972 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1758. Min Act: -0.0001

Data Index: 84487 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1428. Min Act: -0.0001

Data Index: 1221596 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1652. Min Act: -0.0001

Data Index: 502796 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1804. Min Act: -0.0001

Data Index: 749852 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1367. Min Act: -0.0001

Data Index: 118240 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1796. Min Act: -0.0001

Data Index: 819782 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1703. Min Act: -0.0001

Data Index: 497562 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1624. Min Act: -0.0001

Data Index: 198473 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1356. Min Act: -0.0001

Data Index: 1612419 (Python Code)

Max Activating Token Index: 305

Text #18

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1485. Min Act: -0.0001

Data Index: 253548 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1622. Min Act: -0.0001

Data Index: 706417 (C4 (Web Text))

Max Activating Token Index: 794