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

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

Neuron 4535 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.5411. Min Act: -0.0000

Data Index: 1243904 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.6633. Min Act: -0.0000

Data Index: 123384 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.7160. Min Act: -0.0000

Data Index: 633082 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.4207. Min Act: -0.0000

Data Index: 1257446 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.3644. Min Act: -0.0000

Data Index: 181172 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.3755. Min Act: -0.0000

Data Index: 960733 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.4581. Min Act: -0.0000

Data Index: 334975 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.4526. Min Act: -0.0000

Data Index: 832316 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.4213. Min Act: -0.0000

Data Index: 44091 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.3288. Min Act: -0.0000

Data Index: 603859 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.4282. Min Act: -0.0000

Data Index: 650929 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.3620. Min Act: -0.0000

Data Index: 1113895 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.3395. Min Act: -0.0000

Data Index: 294470 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.3071. Min Act: -0.0000

Data Index: 583075 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.2029. Min Act: -0.0000

Data Index: 595354 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.2158. Min Act: -0.0000

Data Index: 502760 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.1968. Min Act: -0.0000

Data Index: 966065 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.3459. Min Act: -0.0000

Data Index: 293041 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.1851. Min Act: -0.0000

Data Index: 866766 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.2398. Min Act: -0.0000

Data Index: 263029 (C4 (Web Text))

Max Activating Token Index: 982