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

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

Neuron 1504 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.8984. Min Act: -0.0001

Data Index: 701295 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.8514. Min Act: -0.0001

Data Index: 1041785 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.5686. Min Act: -0.0000

Data Index: 1303572 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.7315. Min Act: -0.0001

Data Index: 1342366 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.5322. Min Act: -0.0000

Data Index: 560948 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.7318. Min Act: -0.0000

Data Index: 718935 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.5327. Min Act: -0.0001

Data Index: 655847 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.5912. Min Act: -0.0001

Data Index: 1159743 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.5764. Min Act: -0.0000

Data Index: 975154 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.5601. Min Act: -0.0000

Data Index: 365130 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.5321. Min Act: -0.0001

Data Index: 1123667 (C4 (Web Text))

Max Activating Token Index: 761

Text #11

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.5490. Min Act: -0.0000

Data Index: 257072 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.4350. Min Act: -0.0000

Data Index: 776365 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.4197. Min Act: -0.0001

Data Index: 1280276 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.5542. Min Act: -0.0001

Data Index: 492013 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.4485. Min Act: -0.0000

Data Index: 627144 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.5324. Min Act: -0.0000

Data Index: 575098 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.4405. Min Act: -0.0000

Data Index: 1301344 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.4046. Min Act: -0.0001

Data Index: 690476 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.5776. Min Act: -0.0000

Data Index: 710931 (C4 (Web Text))

Max Activating Token Index: 244