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

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

Neuron 2754 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.6477. Min Act: -0.0000

Data Index: 1051249 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.6106. Min Act: -0.0000

Data Index: 1418401 (Python Code)

Max Activating Token Index: 257

Text #2

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.6030. Min Act: -0.0000

Data Index: 1441682 (Python Code)

Max Activating Token Index: 847

Text #3

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.5452. Min Act: -0.0000

Data Index: 1269352 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.5413. Min Act: -0.0000

Data Index: 1437313 (Python Code)

Max Activating Token Index: 610

Text #5

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.5677. Min Act: -0.0000

Data Index: 183172 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.4994. Min Act: -0.0000

Data Index: 428707 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.5259. Min Act: -0.0000

Data Index: 1453478 (Python Code)

Max Activating Token Index: 51

Text #8

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.5249. Min Act: -0.0000

Data Index: 1017499 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.5378. Min Act: -0.0000

Data Index: 1482475 (Python Code)

Max Activating Token Index: 81

Text #10

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.5510. Min Act: -0.0000

Data Index: 1519645 (Python Code)

Max Activating Token Index: 998

Text #11

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.5219. Min Act: 0.0000

Data Index: 1495851 (Python Code)

Max Activating Token Index: 103

Text #12

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.5264. Min Act: -0.0000

Data Index: 1558544 (Python Code)

Max Activating Token Index: 152

Text #13

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.5085. Min Act: -0.0000

Data Index: 1600241 (Python Code)

Max Activating Token Index: 746

Text #14

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.5323. Min Act: 0.0000

Data Index: 1627617 (Python Code)

Max Activating Token Index: 761

Text #15

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.4947. Min Act: -0.0000

Data Index: 482334 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.5002. Min Act: -0.0000

Data Index: 1602707 (Python Code)

Max Activating Token Index: 774

Text #17

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.5107. Min Act: -0.0000

Data Index: 1364484 (Python Code)

Max Activating Token Index: 78

Text #18

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.4555. Min Act: -0.0000

Data Index: 761045 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 0.6477. Min Range: -0.6477

Max Act: 0.4817. Min Act: -0.0000

Data Index: 1603976 (Python Code)

Max Activating Token Index: 469