Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4160 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5436. Min Range: -1.5436

Max Act: 1.4587. Min Act: -0.0002

Data Index: 890465 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 1.5436. Min Range: -1.5436

Max Act: 1.5156. Min Act: -0.0002

Data Index: 1011372 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 1.5436. Min Range: -1.5436

Max Act: 1.4583. Min Act: -0.0002

Data Index: 1202702 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 1.5436. Min Range: -1.5436

Max Act: 1.5430. Min Act: -0.0002

Data Index: 211926 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 1.5436. Min Range: -1.5436

Max Act: 1.5388. Min Act: -0.0002

Data Index: 263632 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 1.5436. Min Range: -1.5436

Max Act: 1.5366. Min Act: -0.0002

Data Index: 1248961 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 1.5436. Min Range: -1.5436

Max Act: 1.3966. Min Act: -0.0002

Data Index: 242052 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 1.5436. Min Range: -1.5436

Max Act: 1.3861. Min Act: -0.0002

Data Index: 542189 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 1.5436. Min Range: -1.5436

Max Act: 1.3712. Min Act: -0.0002

Data Index: 422505 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 1.5436. Min Range: -1.5436

Max Act: 1.4301. Min Act: -0.0002

Data Index: 141760 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 1.5436. Min Range: -1.5436

Max Act: 1.3535. Min Act: -0.0002

Data Index: 679373 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 1.5436. Min Range: -1.5436

Max Act: 1.1319. Min Act: -0.0002

Data Index: 49523 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 1.5436. Min Range: -1.5436

Max Act: 1.2761. Min Act: -0.0002

Data Index: 625085 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 1.5436. Min Range: -1.5436

Max Act: 1.3337. Min Act: -0.0002

Data Index: 790689 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 1.5436. Min Range: -1.5436

Max Act: 1.3099. Min Act: -0.0002

Data Index: 1018607 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 1.5436. Min Range: -1.5436

Max Act: 1.2818. Min Act: -0.0002

Data Index: 498325 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 1.5436. Min Range: -1.5436

Max Act: 1.2800. Min Act: -0.0002

Data Index: 864965 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 1.5436. Min Range: -1.5436

Max Act: 1.3894. Min Act: -0.0002

Data Index: 407388 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 1.5436. Min Range: -1.5436

Max Act: 1.5436. Min Act: -0.0002

Data Index: 1346597 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 1.5436. Min Range: -1.5436

Max Act: 1.4197. Min Act: -0.0002

Data Index: 1209200 (C4 (Web Text))

Max Activating Token Index: 911