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

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

Neuron 1662 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: 1.4663. Min Range: -1.4663

Max Act: 1.4663. Min Act: -0.0001

Data Index: 295325 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 1.4663. Min Range: -1.4663

Max Act: 1.3370. Min Act: -0.0001

Data Index: 334733 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 1.4663. Min Range: -1.4663

Max Act: 1.2528. Min Act: -0.0001

Data Index: 653487 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 1.4663. Min Range: -1.4663

Max Act: 1.2160. Min Act: -0.0001

Data Index: 299052 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 1.4663. Min Range: -1.4663

Max Act: 1.2065. Min Act: -0.0001

Data Index: 561985 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 1.4663. Min Range: -1.4663

Max Act: 1.1922. Min Act: -0.0001

Data Index: 1302026 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 1.4663. Min Range: -1.4663

Max Act: 1.1046. Min Act: -0.0001

Data Index: 1034119 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 1.4663. Min Range: -1.4663

Max Act: 1.1750. Min Act: -0.0001

Data Index: 356008 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 1.4663. Min Range: -1.4663

Max Act: 1.0617. Min Act: -0.0001

Data Index: 829242 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 1.4663. Min Range: -1.4663

Max Act: 1.1405. Min Act: -0.0001

Data Index: 407017 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 1.4663. Min Range: -1.4663

Max Act: 1.1598. Min Act: -0.0000

Data Index: 1163865 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 1.4663. Min Range: -1.4663

Max Act: 1.1257. Min Act: -0.0001

Data Index: 805239 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 1.4663. Min Range: -1.4663

Max Act: 1.0602. Min Act: -0.0001

Data Index: 1262337 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 1.4663. Min Range: -1.4663

Max Act: 1.0805. Min Act: -0.0001

Data Index: 471989 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 1.4663. Min Range: -1.4663

Max Act: 1.0912. Min Act: -0.0001

Data Index: 500363 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 1.4663. Min Range: -1.4663

Max Act: 1.1364. Min Act: -0.0001

Data Index: 264221 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 1.4663. Min Range: -1.4663

Max Act: 1.0775. Min Act: -0.0001

Data Index: 805180 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 1.4663. Min Range: -1.4663

Max Act: 1.1041. Min Act: -0.0000

Data Index: 1031758 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 1.4663. Min Range: -1.4663

Max Act: 1.0283. Min Act: -0.0001

Data Index: 110312 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 1.4663. Min Range: -1.4663

Max Act: 1.0918. Min Act: -0.0001

Data Index: 898199 (C4 (Web Text))

Max Activating Token Index: 9