Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3758 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.1437. Min Range: -3.1437

Max Act: 3.0814. Min Act: -0.0000

Data Index: 915386 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 3.1437. Min Range: -3.1437

Max Act: 2.8333. Min Act: -0.0000

Data Index: 1301007 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 3.1437. Min Range: -3.1437

Max Act: 2.7139. Min Act: -0.0000

Data Index: 457033 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 3.1437. Min Range: -3.1437

Max Act: 3.1437. Min Act: -0.0001

Data Index: 14365 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 3.1437. Min Range: -3.1437

Max Act: 2.7087. Min Act: -0.0000

Data Index: 1214798 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 3.1437. Min Range: -3.1437

Max Act: 2.8552. Min Act: -0.0000

Data Index: 462800 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 3.1437. Min Range: -3.1437

Max Act: 2.0426. Min Act: -0.0000

Data Index: 1110882 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 3.1437. Min Range: -3.1437

Max Act: 2.6777. Min Act: -0.0000

Data Index: 1075938 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 3.1437. Min Range: -3.1437

Max Act: 2.7957. Min Act: -0.0001

Data Index: 306821 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 3.1437. Min Range: -3.1437

Max Act: 1.9149. Min Act: -0.0000

Data Index: 635552 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 3.1437. Min Range: -3.1437

Max Act: 2.5028. Min Act: -0.0001

Data Index: 48463 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 3.1437. Min Range: -3.1437

Max Act: 2.7117. Min Act: -0.0000

Data Index: 189502 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 3.1437. Min Range: -3.1437

Max Act: 2.6564. Min Act: -0.0001

Data Index: 598608 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 3.1437. Min Range: -3.1437

Max Act: 2.4612. Min Act: -0.0001

Data Index: 15813 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 3.1437. Min Range: -3.1437

Max Act: 2.3936. Min Act: -0.0001

Data Index: 16846 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 3.1437. Min Range: -3.1437

Max Act: 2.5141. Min Act: -0.0000

Data Index: 1118965 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 3.1437. Min Range: -3.1437

Max Act: 2.3035. Min Act: -0.0001

Data Index: 880292 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 3.1437. Min Range: -3.1437

Max Act: 2.3017. Min Act: -0.0000

Data Index: 1029551 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 3.1437. Min Range: -3.1437

Max Act: 2.3221. Min Act: -0.0000

Data Index: 270821 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 3.1437. Min Range: -3.1437

Max Act: 2.3876. Min Act: -0.0000

Data Index: 147381 (C4 (Web Text))

Max Activating Token Index: 42