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

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

Neuron 3639 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.2033. Min Act: -0.0001

Data Index: 1039531 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1887. Min Act: 0.0001

Data Index: 44922 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1753. Min Act: -0.0000

Data Index: 913598 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1741. Min Act: -0.0000

Data Index: 10045 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1565. Min Act: -0.0001

Data Index: 1158241 (C4 (Web Text))

Max Activating Token Index: 949

Text #5

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1669. Min Act: -0.0000

Data Index: 1356826 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1609. Min Act: -0.0000

Data Index: 958189 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1493. Min Act: -0.0000

Data Index: 747776 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1512. Min Act: -0.0000

Data Index: 1008657 (C4 (Web Text))

Max Activating Token Index: 1010

Text #9

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1418. Min Act: 0.0000

Data Index: 178235 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1415. Min Act: -0.0000

Data Index: 493515 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1488. Min Act: -0.0001

Data Index: 794845 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1393. Min Act: -0.0000

Data Index: 274579 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1408. Min Act: -0.0001

Data Index: 760251 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1410. Min Act: -0.0000

Data Index: 673277 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1358. Min Act: -0.0000

Data Index: 232405 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1342. Min Act: -0.0001

Data Index: 183487 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1344. Min Act: -0.0001

Data Index: 1140761 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1386. Min Act: -0.0001

Data Index: 6794 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1348. Min Act: -0.0000

Data Index: 920267 (C4 (Web Text))

Max Activating Token Index: 95