Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3952 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1288. Min Range: -1.1288

Max Act: 1.0377. Min Act: -0.0001

Data Index: 1654969 (Python Code)

Max Activating Token Index: 867

Text #1

Max Range: 1.1288. Min Range: -1.1288

Max Act: 1.1288. Min Act: -0.0001

Data Index: 1550597 (Python Code)

Max Activating Token Index: 376

Text #2

Max Range: 1.1288. Min Range: -1.1288

Max Act: 1.0040. Min Act: -0.0001

Data Index: 1552294 (Python Code)

Max Activating Token Index: 939

Text #3

Max Range: 1.1288. Min Range: -1.1288

Max Act: 1.0138. Min Act: -0.0001

Data Index: 1362936 (Python Code)

Max Activating Token Index: 8

Text #4

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.9505. Min Act: -0.0001

Data Index: 1449336 (Python Code)

Max Activating Token Index: 11

Text #5

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.9256. Min Act: -0.0001

Data Index: 1595787 (Python Code)

Max Activating Token Index: 167

Text #6

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.9166. Min Act: -0.0001

Data Index: 1553944 (Python Code)

Max Activating Token Index: 17

Text #7

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.9130. Min Act: -0.0001

Data Index: 1610977 (Python Code)

Max Activating Token Index: 393

Text #8

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.8625. Min Act: -0.0001

Data Index: 1387831 (Python Code)

Max Activating Token Index: 865

Text #9

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.8504. Min Act: -0.0001

Data Index: 1604754 (Python Code)

Max Activating Token Index: 93

Text #10

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.9015. Min Act: -0.0002

Data Index: 1372060 (Python Code)

Max Activating Token Index: 197

Text #11

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.8396. Min Act: -0.0001

Data Index: 1413701 (Python Code)

Max Activating Token Index: 296

Text #12

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.8595. Min Act: -0.0001

Data Index: 1624840 (Python Code)

Max Activating Token Index: 906

Text #13

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.8035. Min Act: -0.0001

Data Index: 1438504 (Python Code)

Max Activating Token Index: 943

Text #14

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.8044. Min Act: -0.0001

Data Index: 1397302 (Python Code)

Max Activating Token Index: 100

Text #15

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.8510. Min Act: -0.0001

Data Index: 1453238 (Python Code)

Max Activating Token Index: 135

Text #16

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.8956. Min Act: -0.0001

Data Index: 1555480 (Python Code)

Max Activating Token Index: 260

Text #17

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.8674. Min Act: -0.0001

Data Index: 1599131 (Python Code)

Max Activating Token Index: 489

Text #18

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.8680. Min Act: -0.0001

Data Index: 1394456 (Python Code)

Max Activating Token Index: 942

Text #19

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.8593. Min Act: -0.0001

Data Index: 1618524 (Python Code)

Max Activating Token Index: 972