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

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

Neuron 3314 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: 0.5763. Min Range: -0.5763

Max Act: 0.5763. Min Act: -0.0000

Data Index: 612975 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 0.5763. Min Range: -0.5763

Max Act: 0.4960. Min Act: -0.0000

Data Index: 108946 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 0.5763. Min Range: -0.5763

Max Act: 0.5145. Min Act: -0.0000

Data Index: 676330 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 0.5763. Min Range: -0.5763

Max Act: 0.4934. Min Act: -0.0000

Data Index: 688319 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 0.5763. Min Range: -0.5763

Max Act: 0.4437. Min Act: -0.0000

Data Index: 452485 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 0.5763. Min Range: -0.5763

Max Act: 0.4134. Min Act: -0.0000

Data Index: 121543 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 0.5763. Min Range: -0.5763

Max Act: 0.4399. Min Act: -0.0000

Data Index: 35550 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 0.5763. Min Range: -0.5763

Max Act: 0.4383. Min Act: -0.0000

Data Index: 1336380 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 0.5763. Min Range: -0.5763

Max Act: 0.3824. Min Act: -0.0000

Data Index: 1262153 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 0.5763. Min Range: -0.5763

Max Act: 0.4085. Min Act: -0.0000

Data Index: 215843 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 0.5763. Min Range: -0.5763

Max Act: 0.3909. Min Act: -0.0000

Data Index: 1482269 (Python Code)

Max Activating Token Index: 292

Text #11

Max Range: 0.5763. Min Range: -0.5763

Max Act: 0.4126. Min Act: -0.0000

Data Index: 742122 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 0.5763. Min Range: -0.5763

Max Act: 0.3954. Min Act: -0.0000

Data Index: 1143301 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 0.5763. Min Range: -0.5763

Max Act: 0.3906. Min Act: -0.0000

Data Index: 1258532 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 0.5763. Min Range: -0.5763

Max Act: 0.4264. Min Act: -0.0000

Data Index: 1176136 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 0.5763. Min Range: -0.5763

Max Act: 0.3986. Min Act: -0.0000

Data Index: 71432 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 0.5763. Min Range: -0.5763

Max Act: 0.3804. Min Act: -0.0000

Data Index: 1507054 (Python Code)

Max Activating Token Index: 375

Text #17

Max Range: 0.5763. Min Range: -0.5763

Max Act: 0.3668. Min Act: -0.0000

Data Index: 1506592 (Python Code)

Max Activating Token Index: 207

Text #18

Max Range: 0.5763. Min Range: -0.5763

Max Act: 0.3883. Min Act: -0.0000

Data Index: 506933 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 0.5763. Min Range: -0.5763

Max Act: 0.3700. Min Act: -0.0000

Data Index: 1052944 (C4 (Web Text))

Max Activating Token Index: 491