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

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

Neuron 929 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.8342. Min Range: -6.8342

Max Act: 6.8342. Min Act: -0.0000

Data Index: 1416174 (Python Code)

Max Activating Token Index: 48

Text #1

Max Range: 6.8342. Min Range: -6.8342

Max Act: 6.6059. Min Act: -0.0000

Data Index: 1384476 (Python Code)

Max Activating Token Index: 77

Text #2

Max Range: 6.8342. Min Range: -6.8342

Max Act: 6.6059. Min Act: -0.0000

Data Index: 1467231 (Python Code)

Max Activating Token Index: 77

Text #3

Max Range: 6.8342. Min Range: -6.8342

Max Act: 6.5879. Min Act: -0.0000

Data Index: 1487834 (Python Code)

Max Activating Token Index: 45

Text #4

Max Range: 6.8342. Min Range: -6.8342

Max Act: 6.6803. Min Act: -0.0000

Data Index: 1594477 (Python Code)

Max Activating Token Index: 48

Text #5

Max Range: 6.8342. Min Range: -6.8342

Max Act: 6.6803. Min Act: -0.0000

Data Index: 1385073 (Python Code)

Max Activating Token Index: 48

Text #6

Max Range: 6.8342. Min Range: -6.8342

Max Act: 6.4212. Min Act: -0.0000

Data Index: 1476512 (Python Code)

Max Activating Token Index: 55

Text #7

Max Range: 6.8342. Min Range: -6.8342

Max Act: 6.4140. Min Act: -0.0000

Data Index: 1439072 (Python Code)

Max Activating Token Index: 54

Text #8

Max Range: 6.8342. Min Range: -6.8342

Max Act: 6.4140. Min Act: -0.0000

Data Index: 1542436 (Python Code)

Max Activating Token Index: 54

Text #9

Max Range: 6.8342. Min Range: -6.8342

Max Act: 6.6619. Min Act: -0.0000

Data Index: 1613665 (Python Code)

Max Activating Token Index: 50

Text #10

Max Range: 6.8342. Min Range: -6.8342

Max Act: 6.6418. Min Act: -0.0000

Data Index: 1370316 (Python Code)

Max Activating Token Index: 51

Text #11

Max Range: 6.8342. Min Range: -6.8342

Max Act: 6.4307. Min Act: -0.0000

Data Index: 1379919 (Python Code)

Max Activating Token Index: 78

Text #12

Max Range: 6.8342. Min Range: -6.8342

Max Act: 6.6135. Min Act: -0.0000

Data Index: 1603407 (Python Code)

Max Activating Token Index: 68

Text #13

Max Range: 6.8342. Min Range: -6.8342

Max Act: 6.2508. Min Act: -0.0000

Data Index: 1600976 (Python Code)

Max Activating Token Index: 73

Text #14

Max Range: 6.8342. Min Range: -6.8342

Max Act: 6.4207. Min Act: -0.0000

Data Index: 1572317 (Python Code)

Max Activating Token Index: 74

Text #15

Max Range: 6.8342. Min Range: -6.8342

Max Act: 6.4207. Min Act: -0.0000

Data Index: 1389289 (Python Code)

Max Activating Token Index: 74

Text #16

Max Range: 6.8342. Min Range: -6.8342

Max Act: 6.4207. Min Act: -0.0000

Data Index: 1625676 (Python Code)

Max Activating Token Index: 74

Text #17

Max Range: 6.8342. Min Range: -6.8342

Max Act: 6.6132. Min Act: -0.0000

Data Index: 1498999 (Python Code)

Max Activating Token Index: 53

Text #18

Max Range: 6.8342. Min Range: -6.8342

Max Act: 6.4260. Min Act: -0.0000

Data Index: 1560274 (Python Code)

Max Activating Token Index: 76

Text #19

Max Range: 6.8342. Min Range: -6.8342

Max Act: 6.4260. Min Act: -0.0000

Data Index: 1402617 (Python Code)

Max Activating Token Index: 76