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

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

Neuron 5001 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1027. Min Range: -2.1027

Max Act: 2.1027. Min Act: -0.0000

Data Index: 1476921 (Python Code)

Max Activating Token Index: 88

Text #1

Max Range: 2.1027. Min Range: -2.1027

Max Act: 1.8007. Min Act: -0.0000

Data Index: 1614842 (Python Code)

Max Activating Token Index: 671

Text #2

Max Range: 2.1027. Min Range: -2.1027

Max Act: 1.8838. Min Act: -0.0000

Data Index: 1552725 (Python Code)

Max Activating Token Index: 773

Text #3

Max Range: 2.1027. Min Range: -2.1027

Max Act: 1.8227. Min Act: -0.0000

Data Index: 1459335 (Python Code)

Max Activating Token Index: 532

Text #4

Max Range: 2.1027. Min Range: -2.1027

Max Act: 1.7935. Min Act: -0.0000

Data Index: 1544935 (Python Code)

Max Activating Token Index: 390

Text #5

Max Range: 2.1027. Min Range: -2.1027

Max Act: 1.6734. Min Act: -0.0000

Data Index: 1526316 (Python Code)

Max Activating Token Index: 55

Text #6

Max Range: 2.1027. Min Range: -2.1027

Max Act: 1.7159. Min Act: -0.0000

Data Index: 1494840 (Python Code)

Max Activating Token Index: 962

Text #7

Max Range: 2.1027. Min Range: -2.1027

Max Act: 1.6213. Min Act: -0.0000

Data Index: 1449265 (Python Code)

Max Activating Token Index: 881

Text #8

Max Range: 2.1027. Min Range: -2.1027

Max Act: 1.5847. Min Act: -0.0000

Data Index: 1467972 (Python Code)

Max Activating Token Index: 992

Text #9

Max Range: 2.1027. Min Range: -2.1027

Max Act: 1.5747. Min Act: -0.0000

Data Index: 1578010 (Python Code)

Max Activating Token Index: 235

Text #10

Max Range: 2.1027. Min Range: -2.1027

Max Act: 1.5455. Min Act: -0.0000

Data Index: 1463062 (Python Code)

Max Activating Token Index: 328

Text #11

Max Range: 2.1027. Min Range: -2.1027

Max Act: 1.5376. Min Act: -0.0000

Data Index: 1435402 (Python Code)

Max Activating Token Index: 698

Text #12

Max Range: 2.1027. Min Range: -2.1027

Max Act: 1.3867. Min Act: -0.0000

Data Index: 1545366 (Python Code)

Max Activating Token Index: 849

Text #13

Max Range: 2.1027. Min Range: -2.1027

Max Act: 1.4372. Min Act: -0.0000

Data Index: 1473842 (Python Code)

Max Activating Token Index: 140

Text #14

Max Range: 2.1027. Min Range: -2.1027

Max Act: 1.3312. Min Act: -0.0000

Data Index: 1653230 (Python Code)

Max Activating Token Index: 728

Text #15

Max Range: 2.1027. Min Range: -2.1027

Max Act: 1.4762. Min Act: -0.0000

Data Index: 1454939 (Python Code)

Max Activating Token Index: 193

Text #16

Max Range: 2.1027. Min Range: -2.1027

Max Act: 1.4651. Min Act: -0.0000

Data Index: 1414124 (Python Code)

Max Activating Token Index: 804

Text #17

Max Range: 2.1027. Min Range: -2.1027

Max Act: 1.4574. Min Act: -0.0000

Data Index: 1477834 (Python Code)

Max Activating Token Index: 679

Text #18

Max Range: 2.1027. Min Range: -2.1027

Max Act: 1.3395. Min Act: -0.0000

Data Index: 1655031 (Python Code)

Max Activating Token Index: 632

Text #19

Max Range: 2.1027. Min Range: -2.1027

Max Act: 1.3197. Min Act: -0.0000

Data Index: 1421129 (Python Code)

Max Activating Token Index: 733