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

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

Neuron 2355 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1855. Min Range: -3.1855

Max Act: 3.1855. Min Act: -0.0000

Data Index: 356373 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.1855. Min Range: -3.1855

Max Act: 3.0303. Min Act: -0.0000

Data Index: 255927 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 3.1855. Min Range: -3.1855

Max Act: 2.8330. Min Act: -0.0000

Data Index: 71444 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 3.1855. Min Range: -3.1855

Max Act: 2.7473. Min Act: -0.0000

Data Index: 415125 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 3.1855. Min Range: -3.1855

Max Act: 2.4771. Min Act: -0.0000

Data Index: 82716 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 3.1855. Min Range: -3.1855

Max Act: 2.4956. Min Act: -0.0000

Data Index: 392967 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 3.1855. Min Range: -3.1855

Max Act: 2.5128. Min Act: -0.0000

Data Index: 56916 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 3.1855. Min Range: -3.1855

Max Act: 2.4946. Min Act: -0.0000

Data Index: 1281068 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 3.1855. Min Range: -3.1855

Max Act: 2.2475. Min Act: -0.0000

Data Index: 611418 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 3.1855. Min Range: -3.1855

Max Act: 2.2242. Min Act: -0.0000

Data Index: 76895 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 3.1855. Min Range: -3.1855

Max Act: 2.2782. Min Act: -0.0000

Data Index: 702752 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 3.1855. Min Range: -3.1855

Max Act: 1.9889. Min Act: -0.0000

Data Index: 1445685 (Python Code)

Max Activating Token Index: 338

Text #12

Max Range: 3.1855. Min Range: -3.1855

Max Act: 2.0300. Min Act: -0.0000

Data Index: 921329 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 3.1855. Min Range: -3.1855

Max Act: 2.0173. Min Act: -0.0000

Data Index: 1111963 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 3.1855. Min Range: -3.1855

Max Act: 1.9924. Min Act: -0.0000

Data Index: 309289 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 3.1855. Min Range: -3.1855

Max Act: 2.1644. Min Act: -0.0000

Data Index: 993552 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 3.1855. Min Range: -3.1855

Max Act: 2.0320. Min Act: -0.0000

Data Index: 488097 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 3.1855. Min Range: -3.1855

Max Act: 1.9243. Min Act: -0.0000

Data Index: 328597 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 3.1855. Min Range: -3.1855

Max Act: 2.0102. Min Act: -0.0000

Data Index: 1089134 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 3.1855. Min Range: -3.1855

Max Act: 1.9405. Min Act: -0.0000

Data Index: 75510 (C4 (Web Text))

Max Activating Token Index: 551