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

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

Neuron 5214 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3471. Min Range: -2.3471

Max Act: 2.3471. Min Act: -0.0000

Data Index: 488077 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 2.3471. Min Range: -2.3471

Max Act: 2.2681. Min Act: -0.0000

Data Index: 1334914 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 2.3471. Min Range: -2.3471

Max Act: 2.1271. Min Act: -0.0000

Data Index: 661793 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 2.3471. Min Range: -2.3471

Max Act: 1.8404. Min Act: -0.0000

Data Index: 889627 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 2.3471. Min Range: -2.3471

Max Act: 1.9598. Min Act: -0.0000

Data Index: 652834 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 2.3471. Min Range: -2.3471

Max Act: 1.7704. Min Act: -0.0000

Data Index: 75376 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 2.3471. Min Range: -2.3471

Max Act: 1.7569. Min Act: -0.0000

Data Index: 251583 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 2.3471. Min Range: -2.3471

Max Act: 1.6170. Min Act: -0.0000

Data Index: 896233 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 2.3471. Min Range: -2.3471

Max Act: 1.6790. Min Act: -0.0000

Data Index: 1080936 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 2.3471. Min Range: -2.3471

Max Act: 1.6696. Min Act: -0.0000

Data Index: 1173780 (C4 (Web Text))

Max Activating Token Index: 635

Text #10

Max Range: 2.3471. Min Range: -2.3471

Max Act: 1.6638. Min Act: -0.0000

Data Index: 840245 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 2.3471. Min Range: -2.3471

Max Act: 1.5645. Min Act: -0.0000

Data Index: 724235 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 2.3471. Min Range: -2.3471

Max Act: 1.6608. Min Act: -0.0000

Data Index: 508589 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 2.3471. Min Range: -2.3471

Max Act: 1.5672. Min Act: -0.0000

Data Index: 999087 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 2.3471. Min Range: -2.3471

Max Act: 1.6432. Min Act: -0.0000

Data Index: 1113106 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 2.3471. Min Range: -2.3471

Max Act: 1.6384. Min Act: -0.0000

Data Index: 649861 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 2.3471. Min Range: -2.3471

Max Act: 1.5473. Min Act: -0.0000

Data Index: 859119 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 2.3471. Min Range: -2.3471

Max Act: 1.6081. Min Act: -0.0000

Data Index: 790078 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 2.3471. Min Range: -2.3471

Max Act: 1.6045. Min Act: -0.0000

Data Index: 1037457 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 2.3471. Min Range: -2.3471

Max Act: 1.5889. Min Act: -0.0000

Data Index: 23895 (C4 (Web Text))

Max Activating Token Index: 327