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

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

Neuron 2123 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: 4.0493. Min Range: -4.0493

Max Act: 3.9672. Min Act: -0.0000

Data Index: 947008 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 4.0493. Min Range: -4.0493

Max Act: 3.7394. Min Act: -0.0000

Data Index: 446958 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 4.0493. Min Range: -4.0493

Max Act: 4.0493. Min Act: -0.0000

Data Index: 1090330 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 4.0493. Min Range: -4.0493

Max Act: 3.5757. Min Act: -0.0000

Data Index: 276290 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 4.0493. Min Range: -4.0493

Max Act: 3.6593. Min Act: -0.0000

Data Index: 683818 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 4.0493. Min Range: -4.0493

Max Act: 3.2887. Min Act: -0.0000

Data Index: 88162 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 4.0493. Min Range: -4.0493

Max Act: 3.1698. Min Act: -0.0000

Data Index: 803877 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 4.0493. Min Range: -4.0493

Max Act: 2.5868. Min Act: -0.0000

Data Index: 353858 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 4.0493. Min Range: -4.0493

Max Act: 2.4166. Min Act: -0.0000

Data Index: 976260 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 4.0493. Min Range: -4.0493

Max Act: 2.4372. Min Act: -0.0000

Data Index: 907132 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 4.0493. Min Range: -4.0493

Max Act: 2.7211. Min Act: -0.0000

Data Index: 1351336 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 4.0493. Min Range: -4.0493

Max Act: 2.5125. Min Act: -0.0000

Data Index: 153428 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 4.0493. Min Range: -4.0493

Max Act: 2.1206. Min Act: -0.0000

Data Index: 366460 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 4.0493. Min Range: -4.0493

Max Act: 2.4960. Min Act: -0.0000

Data Index: 638279 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 4.0493. Min Range: -4.0493

Max Act: 2.3218. Min Act: -0.0000

Data Index: 330263 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 4.0493. Min Range: -4.0493

Max Act: 2.3456. Min Act: -0.0000

Data Index: 673100 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 4.0493. Min Range: -4.0493

Max Act: 2.4447. Min Act: -0.0000

Data Index: 575619 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 4.0493. Min Range: -4.0493

Max Act: 2.6374. Min Act: -0.0000

Data Index: 102380 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 4.0493. Min Range: -4.0493

Max Act: 2.5018. Min Act: -0.0000

Data Index: 855050 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 4.0493. Min Range: -4.0493

Max Act: 2.2958. Min Act: -0.0000

Data Index: 1173810 (C4 (Web Text))

Max Activating Token Index: 134