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

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

Neuron 5230 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7410. Min Range: -4.7410

Max Act: 4.7410. Min Act: -0.0000

Data Index: 237392 (C4 (Web Text))

Max Activating Token Index: 202

Text #1

Max Range: 4.7410. Min Range: -4.7410

Max Act: 4.7373. Min Act: -0.0000

Data Index: 1130330 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 4.7410. Min Range: -4.7410

Max Act: 4.4231. Min Act: -0.0000

Data Index: 854042 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 4.7410. Min Range: -4.7410

Max Act: 4.4004. Min Act: -0.0000

Data Index: 262811 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 4.7410. Min Range: -4.7410

Max Act: 4.3803. Min Act: -0.0000

Data Index: 1222824 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 4.7410. Min Range: -4.7410

Max Act: 4.0453. Min Act: -0.0000

Data Index: 1045251 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 4.7410. Min Range: -4.7410

Max Act: 4.3522. Min Act: -0.0000

Data Index: 495180 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 4.7410. Min Range: -4.7410

Max Act: 3.9066. Min Act: -0.0000

Data Index: 531080 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 4.7410. Min Range: -4.7410

Max Act: 3.8696. Min Act: -0.0000

Data Index: 912702 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 4.7410. Min Range: -4.7410

Max Act: 4.0179. Min Act: -0.0000

Data Index: 1215573 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 4.7410. Min Range: -4.7410

Max Act: 4.3294. Min Act: -0.0000

Data Index: 213511 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 4.7410. Min Range: -4.7410

Max Act: 3.7206. Min Act: -0.0000

Data Index: 298496 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 4.7410. Min Range: -4.7410

Max Act: 3.7058. Min Act: -0.0000

Data Index: 596580 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 4.7410. Min Range: -4.7410

Max Act: 3.8494. Min Act: -0.0000

Data Index: 741085 (C4 (Web Text))

Max Activating Token Index: 919

Text #14

Max Range: 4.7410. Min Range: -4.7410

Max Act: 3.8619. Min Act: -0.0000

Data Index: 328952 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 4.7410. Min Range: -4.7410

Max Act: 3.5892. Min Act: -0.0000

Data Index: 835724 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 4.7410. Min Range: -4.7410

Max Act: 3.7090. Min Act: -0.0000

Data Index: 1142484 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 4.7410. Min Range: -4.7410

Max Act: 3.7026. Min Act: -0.0000

Data Index: 219661 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 4.7410. Min Range: -4.7410

Max Act: 3.6846. Min Act: -0.0000

Data Index: 122217 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 4.7410. Min Range: -4.7410

Max Act: 3.3691. Min Act: -0.0000

Data Index: 1133017 (C4 (Web Text))

Max Activating Token Index: 341