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

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

Neuron 678 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3874. Min Range: -5.3874

Max Act: 5.3874. Min Act: -0.0000

Data Index: 496034 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 5.3874. Min Range: -5.3874

Max Act: 5.3172. Min Act: -0.0000

Data Index: 591450 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 5.3874. Min Range: -5.3874

Max Act: 5.0629. Min Act: -0.0000

Data Index: 721036 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 5.3874. Min Range: -5.3874

Max Act: 5.2116. Min Act: -0.0000

Data Index: 478176 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 5.3874. Min Range: -5.3874

Max Act: 4.1969. Min Act: -0.0000

Data Index: 1280313 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 5.3874. Min Range: -5.3874

Max Act: 4.2040. Min Act: -0.0000

Data Index: 531591 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 5.3874. Min Range: -5.3874

Max Act: 4.4470. Min Act: -0.0000

Data Index: 51681 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 5.3874. Min Range: -5.3874

Max Act: 4.2176. Min Act: -0.0000

Data Index: 980210 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 5.3874. Min Range: -5.3874

Max Act: 3.6266. Min Act: -0.0000

Data Index: 1343248 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 5.3874. Min Range: -5.3874

Max Act: 4.0717. Min Act: -0.0000

Data Index: 1222100 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 5.3874. Min Range: -5.3874

Max Act: 3.9816. Min Act: -0.0000

Data Index: 545441 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 5.3874. Min Range: -5.3874

Max Act: 4.3127. Min Act: -0.0000

Data Index: 863084 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 5.3874. Min Range: -5.3874

Max Act: 3.7008. Min Act: -0.0000

Data Index: 10939 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 5.3874. Min Range: -5.3874

Max Act: 3.6152. Min Act: -0.0000

Data Index: 835216 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 5.3874. Min Range: -5.3874

Max Act: 3.7362. Min Act: -0.0000

Data Index: 385856 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 5.3874. Min Range: -5.3874

Max Act: 3.5691. Min Act: 0.0001

Data Index: 596899 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 5.3874. Min Range: -5.3874

Max Act: 3.8273. Min Act: 0.0000

Data Index: 1003310 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 5.3874. Min Range: -5.3874

Max Act: 3.7191. Min Act: 0.0002

Data Index: 632929 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 5.3874. Min Range: -5.3874

Max Act: 3.6640. Min Act: -0.0000

Data Index: 820159 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 5.3874. Min Range: -5.3874

Max Act: 3.4696. Min Act: -0.0000

Data Index: 992846 (C4 (Web Text))

Max Activating Token Index: 455