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

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

Neuron 5054 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2913. Min Range: -2.2913

Max Act: 2.2913. Min Act: -0.0000

Data Index: 1466545 (Python Code)

Max Activating Token Index: 1018

Text #1

Max Range: 2.2913. Min Range: -2.2913

Max Act: 1.9183. Min Act: -0.0000

Data Index: 1599315 (Python Code)

Max Activating Token Index: 974

Text #2

Max Range: 2.2913. Min Range: -2.2913

Max Act: 1.9855. Min Act: -0.0000

Data Index: 1475416 (Python Code)

Max Activating Token Index: 407

Text #3

Max Range: 2.2913. Min Range: -2.2913

Max Act: 1.9372. Min Act: -0.0000

Data Index: 1424998 (Python Code)

Max Activating Token Index: 646

Text #4

Max Range: 2.2913. Min Range: -2.2913

Max Act: 2.0044. Min Act: -0.0000

Data Index: 1457087 (Python Code)

Max Activating Token Index: 496

Text #5

Max Range: 2.2913. Min Range: -2.2913

Max Act: 1.8938. Min Act: -0.0000

Data Index: 1507130 (Python Code)

Max Activating Token Index: 685

Text #6

Max Range: 2.2913. Min Range: -2.2913

Max Act: 1.7492. Min Act: -0.0000

Data Index: 1540435 (Python Code)

Max Activating Token Index: 876

Text #7

Max Range: 2.2913. Min Range: -2.2913

Max Act: 1.7150. Min Act: -0.0000

Data Index: 1526134 (Python Code)

Max Activating Token Index: 933

Text #8

Max Range: 2.2913. Min Range: -2.2913

Max Act: 1.6571. Min Act: -0.0000

Data Index: 1652014 (Python Code)

Max Activating Token Index: 493

Text #9

Max Range: 2.2913. Min Range: -2.2913

Max Act: 1.5000. Min Act: -0.0000

Data Index: 459258 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 2.2913. Min Range: -2.2913

Max Act: 1.4402. Min Act: -0.0000

Data Index: 1571876 (Python Code)

Max Activating Token Index: 842

Text #11

Max Range: 2.2913. Min Range: -2.2913

Max Act: 1.4707. Min Act: -0.0000

Data Index: 1452598 (Python Code)

Max Activating Token Index: 909

Text #12

Max Range: 2.2913. Min Range: -2.2913

Max Act: 1.5094. Min Act: -0.0000

Data Index: 408740 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 2.2913. Min Range: -2.2913

Max Act: 1.2949. Min Act: -0.0000

Data Index: 1586723 (Python Code)

Max Activating Token Index: 371

Text #14

Max Range: 2.2913. Min Range: -2.2913

Max Act: 1.4449. Min Act: -0.0000

Data Index: 1476945 (Python Code)

Max Activating Token Index: 731

Text #15

Max Range: 2.2913. Min Range: -2.2913

Max Act: 1.4469. Min Act: -0.0000

Data Index: 1562311 (Python Code)

Max Activating Token Index: 840

Text #16

Max Range: 2.2913. Min Range: -2.2913

Max Act: 1.3501. Min Act: -0.0000

Data Index: 1372307 (Python Code)

Max Activating Token Index: 963

Text #17

Max Range: 2.2913. Min Range: -2.2913

Max Act: 1.4784. Min Act: -0.0000

Data Index: 1570390 (Python Code)

Max Activating Token Index: 959

Text #18

Max Range: 2.2913. Min Range: -2.2913

Max Act: 1.3721. Min Act: -0.0000

Data Index: 1581073 (Python Code)

Max Activating Token Index: 446

Text #19

Max Range: 2.2913. Min Range: -2.2913

Max Act: 1.3613. Min Act: -0.0000

Data Index: 1430153 (Python Code)

Max Activating Token Index: 551