Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 145 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.3197. Min Act: -0.0000

Data Index: 945820 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.2949. Min Act: -0.0000

Data Index: 302221 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.3585. Min Act: -0.0000

Data Index: 676574 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.5050. Min Act: -0.0000

Data Index: 60874 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.2587. Min Act: -0.0000

Data Index: 936886 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.2428. Min Act: -0.0000

Data Index: 1023686 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.3915. Min Act: -0.0000

Data Index: 373246 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.2862. Min Act: -0.0000

Data Index: 704616 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.2141. Min Act: -0.0000

Data Index: 268109 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.3232. Min Act: -0.0000

Data Index: 441824 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.2528. Min Act: -0.0000

Data Index: 468122 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.0523. Min Act: -0.0000

Data Index: 1061611 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.2711. Min Act: -0.0000

Data Index: 983270 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.1192. Min Act: -0.0000

Data Index: 493035 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.2516. Min Act: -0.0000

Data Index: 109979 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.2603. Min Act: -0.0000

Data Index: 340497 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.2410. Min Act: -0.0000

Data Index: 412637 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.1531. Min Act: -0.0000

Data Index: 26725 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.0753. Min Act: -0.0000

Data Index: 349998 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.1253. Min Act: -0.0000

Data Index: 544192 (C4 (Web Text))

Max Activating Token Index: 189