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

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

Neuron 1855 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.4451. Min Act: -0.0000

Data Index: 1340177 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.2858. Min Act: -0.0000

Data Index: 1352631 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.2790. Min Act: -0.0001

Data Index: 392270 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.2205. Min Act: -0.0001

Data Index: 750095 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.1573. Min Act: -0.0001

Data Index: 608336 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.2505. Min Act: -0.0001

Data Index: 7750 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.1026. Min Act: -0.0001

Data Index: 1269591 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.2570. Min Act: -0.0001

Data Index: 663012 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.1361. Min Act: -0.0001

Data Index: 969923 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.1859. Min Act: -0.0000

Data Index: 340523 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.1032. Min Act: -0.0001

Data Index: 1326329 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.1526. Min Act: -0.0001

Data Index: 262216 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.0920. Min Act: -0.0000

Data Index: 927653 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.1421. Min Act: -0.0000

Data Index: 271033 (C4 (Web Text))

Max Activating Token Index: 515

Text #14

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.0336. Min Act: -0.0001

Data Index: 412844 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.0370. Min Act: -0.0001

Data Index: 1182854 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.0405. Min Act: -0.0001

Data Index: 534750 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 1.4451. Min Range: -1.4451

Max Act: 0.9945. Min Act: -0.0001

Data Index: 439029 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.0851. Min Act: -0.0000

Data Index: 1003613 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.0187. Min Act: -0.0001

Data Index: 984418 (C4 (Web Text))

Max Activating Token Index: 474