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

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

Neuron 5745 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4871. Min Range: -2.4871

Max Act: 2.3047. Min Act: -0.0000

Data Index: 579293 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 2.4871. Min Range: -2.4871

Max Act: 2.4871. Min Act: -0.0001

Data Index: 711332 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 2.4871. Min Range: -2.4871

Max Act: 1.7730. Min Act: -0.0000

Data Index: 730630 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 2.4871. Min Range: -2.4871

Max Act: 1.6477. Min Act: -0.0000

Data Index: 1241505 (C4 (Web Text))

Max Activating Token Index: 468

Text #4

Max Range: 2.4871. Min Range: -2.4871

Max Act: 1.4596. Min Act: -0.0001

Data Index: 716924 (C4 (Web Text))

Max Activating Token Index: 440

Text #5

Max Range: 2.4871. Min Range: -2.4871

Max Act: 1.7205. Min Act: -0.0000

Data Index: 389973 (C4 (Web Text))

Max Activating Token Index: 505

Text #6

Max Range: 2.4871. Min Range: -2.4871

Max Act: 1.8351. Min Act: -0.0000

Data Index: 518324 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 2.4871. Min Range: -2.4871

Max Act: 1.5585. Min Act: -0.0001

Data Index: 1353665 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 2.4871. Min Range: -2.4871

Max Act: 1.5778. Min Act: -0.0001

Data Index: 1229221 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 2.4871. Min Range: -2.4871

Max Act: 1.5741. Min Act: -0.0001

Data Index: 1184577 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 2.4871. Min Range: -2.4871

Max Act: 1.7344. Min Act: -0.0001

Data Index: 907107 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 2.4871. Min Range: -2.4871

Max Act: 1.4225. Min Act: -0.0000

Data Index: 477811 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 2.4871. Min Range: -2.4871

Max Act: 1.4545. Min Act: -0.0000

Data Index: 872642 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 2.4871. Min Range: -2.4871

Max Act: 1.3836. Min Act: -0.0000

Data Index: 1231303 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 2.4871. Min Range: -2.4871

Max Act: 1.5636. Min Act: -0.0000

Data Index: 1191782 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 2.4871. Min Range: -2.4871

Max Act: 1.4677. Min Act: -0.0000

Data Index: 846415 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 2.4871. Min Range: -2.4871

Max Act: 1.4186. Min Act: -0.0001

Data Index: 433160 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 2.4871. Min Range: -2.4871

Max Act: 1.3354. Min Act: -0.0001

Data Index: 247500 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 2.4871. Min Range: -2.4871

Max Act: 1.4900. Min Act: -0.0001

Data Index: 1159702 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 2.4871. Min Range: -2.4871

Max Act: 1.4322. Min Act: -0.0000

Data Index: 777922 (C4 (Web Text))

Max Activating Token Index: 920