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

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

Neuron 5672 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: 0.2614. Min Range: -0.2614

Max Act: 0.2614. Min Act: -0.0000

Data Index: 1457983 (Python Code)

Max Activating Token Index: 535

Text #1

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2497. Min Act: -0.0000

Data Index: 1494693 (Python Code)

Max Activating Token Index: 721

Text #2

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2364. Min Act: -0.0000

Data Index: 1633606 (Python Code)

Max Activating Token Index: 402

Text #3

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2280. Min Act: -0.0000

Data Index: 1506518 (Python Code)

Max Activating Token Index: 930

Text #4

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2270. Min Act: -0.0000

Data Index: 706183 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2240. Min Act: -0.0000

Data Index: 333135 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2090. Min Act: -0.0000

Data Index: 1018914 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2319. Min Act: -0.0000

Data Index: 30828 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2134. Min Act: -0.0000

Data Index: 92055 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2079. Min Act: -0.0000

Data Index: 905648 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2137. Min Act: -0.0000

Data Index: 410718 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2181. Min Act: -0.0000

Data Index: 403793 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.1868. Min Act: -0.0000

Data Index: 811565 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.1986. Min Act: -0.0000

Data Index: 1129317 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2047. Min Act: -0.0000

Data Index: 1278235 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.1893. Min Act: -0.0000

Data Index: 375104 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.1948. Min Act: -0.0000

Data Index: 393170 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.1883. Min Act: -0.0000

Data Index: 82480 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2124. Min Act: -0.0000

Data Index: 1177094 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2190. Min Act: -0.0000

Data Index: 1083163 (C4 (Web Text))

Max Activating Token Index: 122