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

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

Neuron 2372 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0834. Min Range: -7.0834

Max Act: 7.0834. Min Act: -0.0000

Data Index: 271364 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 7.0834. Min Range: -7.0834

Max Act: 7.0459. Min Act: -0.0000

Data Index: 1204046 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 7.0834. Min Range: -7.0834

Max Act: 6.8755. Min Act: -0.0000

Data Index: 785213 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 7.0834. Min Range: -7.0834

Max Act: 7.0235. Min Act: -0.0000

Data Index: 383129 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 7.0834. Min Range: -7.0834

Max Act: 6.6696. Min Act: -0.0000

Data Index: 1314437 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 7.0834. Min Range: -7.0834

Max Act: 6.8330. Min Act: -0.0000

Data Index: 774803 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 7.0834. Min Range: -7.0834

Max Act: 6.6491. Min Act: -0.0000

Data Index: 913374 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 7.0834. Min Range: -7.0834

Max Act: 6.4109. Min Act: -0.0000

Data Index: 1096851 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 7.0834. Min Range: -7.0834

Max Act: 6.3641. Min Act: -0.0000

Data Index: 987556 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 7.0834. Min Range: -7.0834

Max Act: 6.5167. Min Act: -0.0000

Data Index: 667459 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 7.0834. Min Range: -7.0834

Max Act: 6.3254. Min Act: -0.0000

Data Index: 48424 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 7.0834. Min Range: -7.0834

Max Act: 6.4933. Min Act: -0.0000

Data Index: 1301971 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 7.0834. Min Range: -7.0834

Max Act: 6.4753. Min Act: -0.0000

Data Index: 617127 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 7.0834. Min Range: -7.0834

Max Act: 6.4767. Min Act: -0.0000

Data Index: 31858 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 7.0834. Min Range: -7.0834

Max Act: 6.4699. Min Act: -0.0000

Data Index: 367592 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 7.0834. Min Range: -7.0834

Max Act: 6.2279. Min Act: -0.0000

Data Index: 683140 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 7.0834. Min Range: -7.0834

Max Act: 6.3952. Min Act: -0.0000

Data Index: 588038 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 7.0834. Min Range: -7.0834

Max Act: 6.3894. Min Act: -0.0000

Data Index: 1150962 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 7.0834. Min Range: -7.0834

Max Act: 6.1792. Min Act: -0.0000

Data Index: 1337329 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 7.0834. Min Range: -7.0834

Max Act: 6.3538. Min Act: -0.0000

Data Index: 148818 (C4 (Web Text))

Max Activating Token Index: 694