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

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

Neuron 3316 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.5921. Min Act: -0.0000

Data Index: 719518 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.4967. Min Act: 0.0000

Data Index: 31748 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.3147. Min Act: -0.0000

Data Index: 1206020 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.2620. Min Act: -0.0000

Data Index: 52820 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.2655. Min Act: -0.0000

Data Index: 284009 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.2497. Min Act: -0.0000

Data Index: 14442 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.2421. Min Act: -0.0000

Data Index: 1249231 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.2337. Min Act: -0.0000

Data Index: 50552 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.2342. Min Act: -0.0000

Data Index: 662117 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.1933. Min Act: -0.0000

Data Index: 1217057 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.1838. Min Act: 0.0000

Data Index: 488936 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.0957. Min Act: -0.0000

Data Index: 233295 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.1361. Min Act: -0.0000

Data Index: 145235 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.1111. Min Act: -0.0000

Data Index: 1020507 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.1114. Min Act: -0.0000

Data Index: 459596 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.0997. Min Act: -0.0000

Data Index: 1315197 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.1661. Min Act: -0.0000

Data Index: 90674 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.0258. Min Act: -0.0000

Data Index: 1081233 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.0891. Min Act: -0.0000

Data Index: 548829 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.0695. Min Act: -0.0000

Data Index: 625404 (C4 (Web Text))

Max Activating Token Index: 120