Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1325 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1128. Min Range: -1.1128

Max Act: 1.0790. Min Act: -0.0001

Data Index: 1118292 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 1.1128. Min Range: -1.1128

Max Act: 1.1089. Min Act: -0.0001

Data Index: 79865 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 1.1128. Min Range: -1.1128

Max Act: 1.1128. Min Act: -0.0001

Data Index: 257354 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 1.1128. Min Range: -1.1128

Max Act: 1.0250. Min Act: -0.0001

Data Index: 866597 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 1.1128. Min Range: -1.1128

Max Act: 1.0039. Min Act: -0.0001

Data Index: 171611 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.9819. Min Act: -0.0001

Data Index: 1256522 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.9489. Min Act: -0.0001

Data Index: 1259324 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.9321. Min Act: -0.0001

Data Index: 916754 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.8888. Min Act: -0.0001

Data Index: 808431 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.8792. Min Act: -0.0001

Data Index: 715792 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.8300. Min Act: -0.0001

Data Index: 1121870 (C4 (Web Text))

Max Activating Token Index: 259

Text #11

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.8992. Min Act: -0.0001

Data Index: 520955 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.8903. Min Act: -0.0001

Data Index: 642417 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.8639. Min Act: -0.0001

Data Index: 971897 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.8658. Min Act: -0.0001

Data Index: 856222 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.8784. Min Act: -0.0001

Data Index: 75173 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.8283. Min Act: -0.0001

Data Index: 536084 (C4 (Web Text))

Max Activating Token Index: 448

Text #17

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.8055. Min Act: -0.0001

Data Index: 1255118 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.8235. Min Act: -0.0001

Data Index: 1097161 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.8188. Min Act: -0.0001

Data Index: 1044335 (C4 (Web Text))

Max Activating Token Index: 430