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

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

Neuron 2248 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: 2.8424. Min Range: -2.8424

Max Act: 2.8424. Min Act: -0.0001

Data Index: 147140 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 2.8424. Min Range: -2.8424

Max Act: 2.8234. Min Act: -0.0001

Data Index: 746829 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 2.8424. Min Range: -2.8424

Max Act: 2.7385. Min Act: -0.0000

Data Index: 942700 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 2.8424. Min Range: -2.8424

Max Act: 2.7280. Min Act: -0.0001

Data Index: 91306 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 2.8424. Min Range: -2.8424

Max Act: 2.5294. Min Act: -0.0000

Data Index: 1011549 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 2.8424. Min Range: -2.8424

Max Act: 2.6100. Min Act: -0.0000

Data Index: 1259139 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 2.8424. Min Range: -2.8424

Max Act: 2.6887. Min Act: -0.0001

Data Index: 525414 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 2.8424. Min Range: -2.8424

Max Act: 2.5291. Min Act: -0.0000

Data Index: 11637 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 2.8424. Min Range: -2.8424

Max Act: 2.5327. Min Act: -0.0001

Data Index: 45712 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 2.8424. Min Range: -2.8424

Max Act: 2.4200. Min Act: -0.0000

Data Index: 575027 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 2.8424. Min Range: -2.8424

Max Act: 2.5064. Min Act: -0.0000

Data Index: 337571 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 2.8424. Min Range: -2.8424

Max Act: 2.4869. Min Act: -0.0000

Data Index: 167720 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 2.8424. Min Range: -2.8424

Max Act: 2.4792. Min Act: -0.0000

Data Index: 611448 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 2.8424. Min Range: -2.8424

Max Act: 2.3398. Min Act: -0.0000

Data Index: 606881 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 2.8424. Min Range: -2.8424

Max Act: 2.4273. Min Act: -0.0000

Data Index: 565365 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 2.8424. Min Range: -2.8424

Max Act: 2.3360. Min Act: -0.0001

Data Index: 1197660 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 2.8424. Min Range: -2.8424

Max Act: 2.4459. Min Act: -0.0000

Data Index: 516569 (C4 (Web Text))

Max Activating Token Index: 735

Text #17

Max Range: 2.8424. Min Range: -2.8424

Max Act: 2.5933. Min Act: -0.0001

Data Index: 1136670 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 2.8424. Min Range: -2.8424

Max Act: 2.4231. Min Act: -0.0000

Data Index: 1102692 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 2.8424. Min Range: -2.8424

Max Act: 2.4476. Min Act: -0.0000

Data Index: 1170324 (C4 (Web Text))

Max Activating Token Index: 909