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

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

Neuron 223 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: 2.8388. Min Range: -2.8388

Max Act: 2.8388. Min Act: -0.0000

Data Index: 349840 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 2.8388. Min Range: -2.8388

Max Act: 2.6979. Min Act: -0.0000

Data Index: 645990 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 2.8388. Min Range: -2.8388

Max Act: 2.5514. Min Act: -0.0000

Data Index: 939843 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 2.8388. Min Range: -2.8388

Max Act: 2.1074. Min Act: -0.0000

Data Index: 38095 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 2.8388. Min Range: -2.8388

Max Act: 2.3273. Min Act: -0.0000

Data Index: 686051 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 2.8388. Min Range: -2.8388

Max Act: 2.0789. Min Act: -0.0000

Data Index: 740756 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 2.8388. Min Range: -2.8388

Max Act: 2.1835. Min Act: -0.0000

Data Index: 401870 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 2.8388. Min Range: -2.8388

Max Act: 2.0394. Min Act: -0.0000

Data Index: 456283 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 2.8388. Min Range: -2.8388

Max Act: 2.1518. Min Act: -0.0000

Data Index: 1176835 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 2.8388. Min Range: -2.8388

Max Act: 2.0037. Min Act: -0.0000

Data Index: 579751 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 2.8388. Min Range: -2.8388

Max Act: 2.2385. Min Act: -0.0000

Data Index: 797078 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 2.8388. Min Range: -2.8388

Max Act: 2.1190. Min Act: -0.0000

Data Index: 332388 (C4 (Web Text))

Max Activating Token Index: 702

Text #12

Max Range: 2.8388. Min Range: -2.8388

Max Act: 2.1113. Min Act: -0.0000

Data Index: 778839 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 2.8388. Min Range: -2.8388

Max Act: 2.1148. Min Act: -0.0000

Data Index: 1193413 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 2.8388. Min Range: -2.8388

Max Act: 2.2180. Min Act: -0.0000

Data Index: 1172035 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 2.8388. Min Range: -2.8388

Max Act: 1.9706. Min Act: -0.0000

Data Index: 613634 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 2.8388. Min Range: -2.8388

Max Act: 1.8896. Min Act: -0.0000

Data Index: 19991 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 2.8388. Min Range: -2.8388

Max Act: 1.8187. Min Act: -0.0000

Data Index: 423409 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 2.8388. Min Range: -2.8388

Max Act: 1.8649. Min Act: -0.0000

Data Index: 12883 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 2.8388. Min Range: -2.8388

Max Act: 1.9583. Min Act: -0.0000

Data Index: 1083362 (C4 (Web Text))

Max Activating Token Index: 348