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

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

Neuron 4872 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8244. Min Range: -1.8244

Max Act: 1.8244. Min Act: -0.0000

Data Index: 158401 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 1.8244. Min Range: -1.8244

Max Act: 1.5043. Min Act: -0.0000

Data Index: 921210 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 1.8244. Min Range: -1.8244

Max Act: 1.1638. Min Act: -0.0000

Data Index: 1105157 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 1.8244. Min Range: -1.8244

Max Act: 1.1805. Min Act: -0.0000

Data Index: 1284604 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 1.8244. Min Range: -1.8244

Max Act: 1.0963. Min Act: -0.0000

Data Index: 67153 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 1.8244. Min Range: -1.8244

Max Act: 0.9905. Min Act: -0.0000

Data Index: 52002 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 1.8244. Min Range: -1.8244

Max Act: 1.0234. Min Act: -0.0000

Data Index: 400649 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 1.8244. Min Range: -1.8244

Max Act: 1.0771. Min Act: -0.0000

Data Index: 62993 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 1.8244. Min Range: -1.8244

Max Act: 0.9691. Min Act: -0.0000

Data Index: 1118850 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 1.8244. Min Range: -1.8244

Max Act: 1.0282. Min Act: -0.0000

Data Index: 164144 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 1.8244. Min Range: -1.8244

Max Act: 0.9665. Min Act: -0.0000

Data Index: 643289 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 1.8244. Min Range: -1.8244

Max Act: 0.8977. Min Act: -0.0000

Data Index: 131980 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 1.8244. Min Range: -1.8244

Max Act: 0.9660. Min Act: -0.0000

Data Index: 185743 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 1.8244. Min Range: -1.8244

Max Act: 0.9154. Min Act: -0.0000

Data Index: 269133 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 1.8244. Min Range: -1.8244

Max Act: 0.9088. Min Act: -0.0000

Data Index: 161085 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 1.8244. Min Range: -1.8244

Max Act: 0.9918. Min Act: -0.0000

Data Index: 390537 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 1.8244. Min Range: -1.8244

Max Act: 0.9525. Min Act: -0.0000

Data Index: 1260968 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 1.8244. Min Range: -1.8244

Max Act: 0.8580. Min Act: -0.0000

Data Index: 625416 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 1.8244. Min Range: -1.8244

Max Act: 0.9087. Min Act: -0.0000

Data Index: 337410 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 1.8244. Min Range: -1.8244

Max Act: 0.8716. Min Act: -0.0000

Data Index: 1254214 (C4 (Web Text))

Max Activating Token Index: 441