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

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

Neuron 351 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3304. Min Range: -1.3304

Max Act: 1.3304. Min Act: -0.0000

Data Index: 1546329 (Python Code)

Max Activating Token Index: 302

Text #1

Max Range: 1.3304. Min Range: -1.3304

Max Act: 1.0324. Min Act: -0.0000

Data Index: 99711 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 1.3304. Min Range: -1.3304

Max Act: 0.9728. Min Act: -0.0000

Data Index: 1400834 (Python Code)

Max Activating Token Index: 419

Text #3

Max Range: 1.3304. Min Range: -1.3304

Max Act: 0.9757. Min Act: -0.0000

Data Index: 1585919 (Python Code)

Max Activating Token Index: 77

Text #4

Max Range: 1.3304. Min Range: -1.3304

Max Act: 0.9100. Min Act: -0.0000

Data Index: 1511295 (Python Code)

Max Activating Token Index: 401

Text #5

Max Range: 1.3304. Min Range: -1.3304

Max Act: 0.8917. Min Act: -0.0000

Data Index: 1617623 (Python Code)

Max Activating Token Index: 219

Text #6

Max Range: 1.3304. Min Range: -1.3304

Max Act: 0.8082. Min Act: -0.0000

Data Index: 1524594 (Python Code)

Max Activating Token Index: 580

Text #7

Max Range: 1.3304. Min Range: -1.3304

Max Act: 0.7768. Min Act: -0.0000

Data Index: 1391887 (Python Code)

Max Activating Token Index: 522

Text #8

Max Range: 1.3304. Min Range: -1.3304

Max Act: 0.7304. Min Act: -0.0000

Data Index: 1534841 (Python Code)

Max Activating Token Index: 120

Text #9

Max Range: 1.3304. Min Range: -1.3304

Max Act: 0.7081. Min Act: -0.0000

Data Index: 1527096 (Python Code)

Max Activating Token Index: 480

Text #10

Max Range: 1.3304. Min Range: -1.3304

Max Act: 0.6821. Min Act: -0.0000

Data Index: 1381813 (Python Code)

Max Activating Token Index: 754

Text #11

Max Range: 1.3304. Min Range: -1.3304

Max Act: 0.7046. Min Act: -0.0000

Data Index: 1372160 (Python Code)

Max Activating Token Index: 94

Text #12

Max Range: 1.3304. Min Range: -1.3304

Max Act: 0.6805. Min Act: -0.0000

Data Index: 1600966 (Python Code)

Max Activating Token Index: 188

Text #13

Max Range: 1.3304. Min Range: -1.3304

Max Act: 0.6419. Min Act: -0.0000

Data Index: 1377632 (Python Code)

Max Activating Token Index: 194

Text #14

Max Range: 1.3304. Min Range: -1.3304

Max Act: 0.6879. Min Act: -0.0000

Data Index: 1470480 (Python Code)

Max Activating Token Index: 497

Text #15

Max Range: 1.3304. Min Range: -1.3304

Max Act: 0.6001. Min Act: -0.0000

Data Index: 1639002 (Python Code)

Max Activating Token Index: 294

Text #16

Max Range: 1.3304. Min Range: -1.3304

Max Act: 0.6632. Min Act: -0.0000

Data Index: 1622499 (Python Code)

Max Activating Token Index: 381

Text #17

Max Range: 1.3304. Min Range: -1.3304

Max Act: 0.5925. Min Act: -0.0000

Data Index: 1422322 (Python Code)

Max Activating Token Index: 254

Text #18

Max Range: 1.3304. Min Range: -1.3304

Max Act: 0.6387. Min Act: -0.0000

Data Index: 1535511 (Python Code)

Max Activating Token Index: 966

Text #19

Max Range: 1.3304. Min Range: -1.3304

Max Act: 0.6306. Min Act: -0.0000

Data Index: 1505924 (Python Code)

Max Activating Token Index: 960