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

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

Neuron 3927 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: 2.3644. Min Range: -2.3644

Max Act: 2.3644. Min Act: -0.0000

Data Index: 500100 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 2.3644. Min Range: -2.3644

Max Act: 1.8864. Min Act: -0.0000

Data Index: 1030651 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 2.3644. Min Range: -2.3644

Max Act: 1.9554. Min Act: 0.0000

Data Index: 185863 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 2.3644. Min Range: -2.3644

Max Act: 1.8243. Min Act: -0.0000

Data Index: 494897 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 2.3644. Min Range: -2.3644

Max Act: 1.7515. Min Act: -0.0000

Data Index: 1328372 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 2.3644. Min Range: -2.3644

Max Act: 1.7763. Min Act: 0.0000

Data Index: 322165 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 2.3644. Min Range: -2.3644

Max Act: 1.6400. Min Act: 0.0001

Data Index: 731544 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 2.3644. Min Range: -2.3644

Max Act: 1.5747. Min Act: -0.0000

Data Index: 309093 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 2.3644. Min Range: -2.3644

Max Act: 1.5665. Min Act: 0.0000

Data Index: 62993 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 2.3644. Min Range: -2.3644

Max Act: 1.7782. Min Act: 0.0000

Data Index: 1012903 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 2.3644. Min Range: -2.3644

Max Act: 1.3593. Min Act: -0.0000

Data Index: 1317833 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 2.3644. Min Range: -2.3644

Max Act: 1.5006. Min Act: 0.0001

Data Index: 1146537 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 2.3644. Min Range: -2.3644

Max Act: 1.3742. Min Act: -0.0000

Data Index: 1574859 (Python Code)

Max Activating Token Index: 782

Text #13

Max Range: 2.3644. Min Range: -2.3644

Max Act: 1.2600. Min Act: 0.0000

Data Index: 104315 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 2.3644. Min Range: -2.3644

Max Act: 1.2531. Min Act: -0.0000

Data Index: 285616 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 2.3644. Min Range: -2.3644

Max Act: 1.3020. Min Act: 0.0000

Data Index: 873894 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 2.3644. Min Range: -2.3644

Max Act: 1.3533. Min Act: -0.0000

Data Index: 1304000 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 2.3644. Min Range: -2.3644

Max Act: 1.2890. Min Act: 0.0000

Data Index: 962007 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 2.3644. Min Range: -2.3644

Max Act: 1.2396. Min Act: -0.0000

Data Index: 1330372 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 2.3644. Min Range: -2.3644

Max Act: 1.2316. Min Act: -0.0000

Data Index: 1212274 (C4 (Web Text))

Max Activating Token Index: 540