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

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

Neuron 1521 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: 2.7492. Min Range: -2.7492

Max Act: 2.7492. Min Act: -0.0000

Data Index: 1364358 (Python Code)

Max Activating Token Index: 1018

Text #1

Max Range: 2.7492. Min Range: -2.7492

Max Act: 2.4354. Min Act: -0.0000

Data Index: 1403823 (Python Code)

Max Activating Token Index: 760

Text #2

Max Range: 2.7492. Min Range: -2.7492

Max Act: 2.3291. Min Act: -0.0000

Data Index: 1653678 (Python Code)

Max Activating Token Index: 858

Text #3

Max Range: 2.7492. Min Range: -2.7492

Max Act: 2.2583. Min Act: -0.0000

Data Index: 1503406 (Python Code)

Max Activating Token Index: 16

Text #4

Max Range: 2.7492. Min Range: -2.7492

Max Act: 1.7881. Min Act: -0.0000

Data Index: 1524707 (Python Code)

Max Activating Token Index: 597

Text #5

Max Range: 2.7492. Min Range: -2.7492

Max Act: 1.8846. Min Act: -0.0000

Data Index: 1634110 (Python Code)

Max Activating Token Index: 592

Text #6

Max Range: 2.7492. Min Range: -2.7492

Max Act: 1.8530. Min Act: -0.0000

Data Index: 1406153 (Python Code)

Max Activating Token Index: 892

Text #7

Max Range: 2.7492. Min Range: -2.7492

Max Act: 1.7061. Min Act: -0.0000

Data Index: 1546670 (Python Code)

Max Activating Token Index: 276

Text #8

Max Range: 2.7492. Min Range: -2.7492

Max Act: 1.8380. Min Act: -0.0000

Data Index: 1471092 (Python Code)

Max Activating Token Index: 14

Text #9

Max Range: 2.7492. Min Range: -2.7492

Max Act: 1.7968. Min Act: -0.0000

Data Index: 1400033 (Python Code)

Max Activating Token Index: 599

Text #10

Max Range: 2.7492. Min Range: -2.7492

Max Act: 1.6593. Min Act: -0.0000

Data Index: 1601832 (Python Code)

Max Activating Token Index: 21

Text #11

Max Range: 2.7492. Min Range: -2.7492

Max Act: 1.7154. Min Act: -0.0000

Data Index: 1551128 (Python Code)

Max Activating Token Index: 760

Text #12

Max Range: 2.7492. Min Range: -2.7492

Max Act: 1.7227. Min Act: -0.0000

Data Index: 1594064 (Python Code)

Max Activating Token Index: 760

Text #13

Max Range: 2.7492. Min Range: -2.7492

Max Act: 1.7263. Min Act: -0.0000

Data Index: 1559995 (Python Code)

Max Activating Token Index: 113

Text #14

Max Range: 2.7492. Min Range: -2.7492

Max Act: 1.6963. Min Act: -0.0000

Data Index: 1636136 (Python Code)

Max Activating Token Index: 30

Text #15

Max Range: 2.7492. Min Range: -2.7492

Max Act: 1.5342. Min Act: -0.0000

Data Index: 1547532 (Python Code)

Max Activating Token Index: 911

Text #16

Max Range: 2.7492. Min Range: -2.7492

Max Act: 1.7917. Min Act: -0.0000

Data Index: 1616397 (Python Code)

Max Activating Token Index: 16

Text #17

Max Range: 2.7492. Min Range: -2.7492

Max Act: 1.6710. Min Act: -0.0000

Data Index: 1505766 (Python Code)

Max Activating Token Index: 404

Text #18

Max Range: 2.7492. Min Range: -2.7492

Max Act: 1.6119. Min Act: -0.0000

Data Index: 1626175 (Python Code)

Max Activating Token Index: 216

Text #19

Max Range: 2.7492. Min Range: -2.7492

Max Act: 1.5190. Min Act: -0.0000

Data Index: 1482986 (Python Code)

Max Activating Token Index: 138