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

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

Neuron 3576 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.4496. Min Act: -0.0000

Data Index: 1370362 (Python Code)

Max Activating Token Index: 59

Text #1

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.4296. Min Act: -0.0000

Data Index: 1638024 (Python Code)

Max Activating Token Index: 305

Text #2

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.4143. Min Act: -0.0000

Data Index: 41074 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.3994. Min Act: -0.0000

Data Index: 1424773 (Python Code)

Max Activating Token Index: 766

Text #4

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.4144. Min Act: -0.0000

Data Index: 1655121 (Python Code)

Max Activating Token Index: 271

Text #5

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.3875. Min Act: -0.0000

Data Index: 1629297 (Python Code)

Max Activating Token Index: 102

Text #6

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.3791. Min Act: -0.0000

Data Index: 1419189 (Python Code)

Max Activating Token Index: 124

Text #7

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.3915. Min Act: -0.0000

Data Index: 1656510 (Python Code)

Max Activating Token Index: 146

Text #8

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.3901. Min Act: -0.0000

Data Index: 1602551 (Python Code)

Max Activating Token Index: 138

Text #9

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.3593. Min Act: -0.0000

Data Index: 1453392 (Python Code)

Max Activating Token Index: 681

Text #10

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.3890. Min Act: -0.0000

Data Index: 1614997 (Python Code)

Max Activating Token Index: 149

Text #11

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.3975. Min Act: -0.0000

Data Index: 1287402 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.3906. Min Act: -0.0000

Data Index: 1396577 (Python Code)

Max Activating Token Index: 178

Text #13

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.3716. Min Act: -0.0000

Data Index: 1363960 (Python Code)

Max Activating Token Index: 94

Text #14

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.3529. Min Act: -0.0000

Data Index: 1263172 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.3416. Min Act: -0.0000

Data Index: 1622388 (Python Code)

Max Activating Token Index: 140

Text #16

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.3468. Min Act: -0.0000

Data Index: 258840 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.3486. Min Act: -0.0000

Data Index: 1518232 (Python Code)

Max Activating Token Index: 150

Text #18

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.3346. Min Act: -0.0000

Data Index: 1515419 (Python Code)

Max Activating Token Index: 39

Text #19

Max Range: 0.4496. Min Range: -0.4496

Max Act: 0.3551. Min Act: -0.0000

Data Index: 1643943 (Python Code)

Max Activating Token Index: 139