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

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

Neuron 3788 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: 0.6403. Min Range: -0.6403

Max Act: 0.6403. Min Act: -0.0000

Data Index: 300301 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5731. Min Act: -0.0000

Data Index: 1272966 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.3863. Min Act: -0.0001

Data Index: 257855 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.4035. Min Act: -0.0000

Data Index: 722004 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.3976. Min Act: -0.0000

Data Index: 668269 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.3694. Min Act: -0.0000

Data Index: 853320 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.3422. Min Act: -0.0000

Data Index: 594515 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.3904. Min Act: -0.0000

Data Index: 333828 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.3490. Min Act: -0.0000

Data Index: 306598 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.3979. Min Act: -0.0000

Data Index: 81273 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.3456. Min Act: -0.0000

Data Index: 1248587 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.3646. Min Act: -0.0001

Data Index: 245752 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.3721. Min Act: -0.0000

Data Index: 1005361 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.3396. Min Act: -0.0000

Data Index: 1119556 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.3360. Min Act: -0.0000

Data Index: 1016652 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.3472. Min Act: -0.0000

Data Index: 35935 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.3637. Min Act: -0.0000

Data Index: 1216811 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.3564. Min Act: -0.0000

Data Index: 99046 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.3591. Min Act: -0.0000

Data Index: 472793 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.3308. Min Act: -0.0001

Data Index: 954566 (C4 (Web Text))

Max Activating Token Index: 677