Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1563 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.3887. Min Act: -0.0000

Data Index: 882540 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.3658. Min Act: -0.0001

Data Index: 610415 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.3486. Min Act: 0.0001

Data Index: 170655 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.3529. Min Act: -0.0001

Data Index: 527794 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.3325. Min Act: -0.0001

Data Index: 445177 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.3258. Min Act: -0.0000

Data Index: 13657 (C4 (Web Text))

Max Activating Token Index: 532

Text #6

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.3146. Min Act: -0.0001

Data Index: 391553 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.3135. Min Act: -0.0001

Data Index: 1307848 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.3149. Min Act: -0.0001

Data Index: 1021590 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.3132. Min Act: -0.0001

Data Index: 8416 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.3030. Min Act: -0.0001

Data Index: 373775 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.3103. Min Act: -0.0000

Data Index: 175632 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.2983. Min Act: -0.0001

Data Index: 385674 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.3138. Min Act: -0.0001

Data Index: 1349397 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.3125. Min Act: -0.0001

Data Index: 852294 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.2938. Min Act: 0.0000

Data Index: 670757 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.3018. Min Act: -0.0000

Data Index: 441940 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.3006. Min Act: -0.0001

Data Index: 1358795 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.3003. Min Act: -0.0001

Data Index: 496963 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.2989. Min Act: -0.0001

Data Index: 908944 (C4 (Web Text))

Max Activating Token Index: 343