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

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

Neuron 3810 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: 3.3202. Min Range: -3.3202

Max Act: 3.3202. Min Act: -0.0000

Data Index: 690404 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 3.3202. Min Range: -3.3202

Max Act: 2.5976. Min Act: -0.0000

Data Index: 246034 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 3.3202. Min Range: -3.3202

Max Act: 2.0886. Min Act: -0.0000

Data Index: 337143 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 3.3202. Min Range: -3.3202

Max Act: 1.8791. Min Act: -0.0000

Data Index: 945528 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 3.3202. Min Range: -3.3202

Max Act: 1.5572. Min Act: -0.0000

Data Index: 351788 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 3.3202. Min Range: -3.3202

Max Act: 1.4581. Min Act: -0.0000

Data Index: 56930 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 3.3202. Min Range: -3.3202

Max Act: 1.4184. Min Act: -0.0000

Data Index: 20558 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 3.3202. Min Range: -3.3202

Max Act: 1.4742. Min Act: -0.0000

Data Index: 319384 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 3.3202. Min Range: -3.3202

Max Act: 1.5382. Min Act: -0.0000

Data Index: 294658 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 3.3202. Min Range: -3.3202

Max Act: 1.3398. Min Act: -0.0000

Data Index: 488759 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 3.3202. Min Range: -3.3202

Max Act: 1.4041. Min Act: -0.0000

Data Index: 662435 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 3.3202. Min Range: -3.3202

Max Act: 1.3272. Min Act: -0.0000

Data Index: 460344 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 3.3202. Min Range: -3.3202

Max Act: 1.3868. Min Act: -0.0000

Data Index: 8425 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 3.3202. Min Range: -3.3202

Max Act: 1.3260. Min Act: -0.0000

Data Index: 750381 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 3.3202. Min Range: -3.3202

Max Act: 1.1701. Min Act: -0.0000

Data Index: 1204106 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 3.3202. Min Range: -3.3202

Max Act: 1.3197. Min Act: -0.0000

Data Index: 8747 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 3.3202. Min Range: -3.3202

Max Act: 1.2549. Min Act: -0.0000

Data Index: 776789 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 3.3202. Min Range: -3.3202

Max Act: 1.3304. Min Act: -0.0000

Data Index: 502649 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 3.3202. Min Range: -3.3202

Max Act: 1.2073. Min Act: -0.0000

Data Index: 401173 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 3.3202. Min Range: -3.3202

Max Act: 1.3050. Min Act: -0.0000

Data Index: 1302284 (C4 (Web Text))

Max Activating Token Index: 886