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

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

Neuron 3656 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.9698. Min Act: -0.0001

Data Index: 801649 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.8939. Min Act: -0.0001

Data Index: 342804 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.8241. Min Act: -0.0000

Data Index: 1009460 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.8703. Min Act: -0.0001

Data Index: 940447 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.7855. Min Act: -0.0001

Data Index: 902302 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.8494. Min Act: -0.0001

Data Index: 395746 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.7767. Min Act: -0.0001

Data Index: 899422 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.7448. Min Act: -0.0001

Data Index: 1031748 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.7756. Min Act: -0.0001

Data Index: 1057022 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.7804. Min Act: -0.0001

Data Index: 834440 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.7485. Min Act: -0.0001

Data Index: 477932 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.7512. Min Act: -0.0001

Data Index: 1233588 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.7516. Min Act: -0.0001

Data Index: 1330759 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.6995. Min Act: -0.0001

Data Index: 1327196 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.7361. Min Act: -0.0001

Data Index: 809063 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.7423. Min Act: -0.0001

Data Index: 405256 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.7190. Min Act: -0.0001

Data Index: 1104149 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.7530. Min Act: -0.0001

Data Index: 1135171 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.6861. Min Act: -0.0001

Data Index: 1105026 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.7231. Min Act: -0.0001

Data Index: 161416 (C4 (Web Text))

Max Activating Token Index: 101