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

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

Neuron 2540 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: 0.3987. Min Range: -0.3987

Max Act: 0.3987. Min Act: -0.0000

Data Index: 240884 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.3845. Min Act: -0.0000

Data Index: 1504672 (Python Code)

Max Activating Token Index: 818

Text #2

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.3225. Min Act: -0.0000

Data Index: 243277 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.3297. Min Act: -0.0000

Data Index: 160786 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.3521. Min Act: -0.0000

Data Index: 1279270 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.3518. Min Act: -0.0000

Data Index: 872679 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.3615. Min Act: -0.0000

Data Index: 969674 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.3526. Min Act: -0.0000

Data Index: 353743 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.3347. Min Act: -0.0000

Data Index: 957470 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.3402. Min Act: -0.0000

Data Index: 979178 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.3635. Min Act: -0.0000

Data Index: 490451 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.3363. Min Act: -0.0000

Data Index: 688353 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.3399. Min Act: -0.0000

Data Index: 327444 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.3339. Min Act: -0.0000

Data Index: 907453 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.3234. Min Act: -0.0000

Data Index: 1233174 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.3234. Min Act: -0.0000

Data Index: 1255911 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.3196. Min Act: -0.0000

Data Index: 1201373 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.3079. Min Act: 0.0000

Data Index: 957093 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.3307. Min Act: -0.0000

Data Index: 677291 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.3128. Min Act: -0.0000

Data Index: 595530 (C4 (Web Text))

Max Activating Token Index: 645