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

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

Neuron 1575 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: 0.8326. Min Range: -0.8326

Max Act: 0.8326. Min Act: -0.0001

Data Index: 1562379 (Python Code)

Max Activating Token Index: 933

Text #1

Max Range: 0.8326. Min Range: -0.8326

Max Act: 0.6406. Min Act: -0.0001

Data Index: 1569859 (Python Code)

Max Activating Token Index: 99

Text #2

Max Range: 0.8326. Min Range: -0.8326

Max Act: 0.6592. Min Act: -0.0001

Data Index: 1512804 (Python Code)

Max Activating Token Index: 928

Text #3

Max Range: 0.8326. Min Range: -0.8326

Max Act: 0.4958. Min Act: -0.0000

Data Index: 1656203 (Python Code)

Max Activating Token Index: 784

Text #4

Max Range: 0.8326. Min Range: -0.8326

Max Act: 0.4610. Min Act: -0.0001

Data Index: 1481063 (Python Code)

Max Activating Token Index: 1000

Text #5

Max Range: 0.8326. Min Range: -0.8326

Max Act: 0.4869. Min Act: -0.0000

Data Index: 262093 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.8326. Min Range: -0.8326

Max Act: 0.4785. Min Act: -0.0000

Data Index: 1582656 (Python Code)

Max Activating Token Index: 764

Text #7

Max Range: 0.8326. Min Range: -0.8326

Max Act: 0.4216. Min Act: -0.0001

Data Index: 1588387 (Python Code)

Max Activating Token Index: 318

Text #8

Max Range: 0.8326. Min Range: -0.8326

Max Act: 0.4477. Min Act: -0.0000

Data Index: 898138 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 0.8326. Min Range: -0.8326

Max Act: 0.4098. Min Act: -0.0000

Data Index: 682355 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 0.8326. Min Range: -0.8326

Max Act: 0.4408. Min Act: -0.0000

Data Index: 1101575 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 0.8326. Min Range: -0.8326

Max Act: 0.4530. Min Act: -0.0001

Data Index: 1428763 (Python Code)

Max Activating Token Index: 951

Text #12

Max Range: 0.8326. Min Range: -0.8326

Max Act: 0.4457. Min Act: -0.0001

Data Index: 746412 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 0.8326. Min Range: -0.8326

Max Act: 0.4427. Min Act: -0.0001

Data Index: 760624 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 0.8326. Min Range: -0.8326

Max Act: 0.4602. Min Act: -0.0001

Data Index: 1410529 (Python Code)

Max Activating Token Index: 364

Text #15

Max Range: 0.8326. Min Range: -0.8326

Max Act: 0.4183. Min Act: -0.0001

Data Index: 925749 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 0.8326. Min Range: -0.8326

Max Act: 0.3728. Min Act: -0.0000

Data Index: 671293 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 0.8326. Min Range: -0.8326

Max Act: 0.4611. Min Act: -0.0001

Data Index: 1394892 (Python Code)

Max Activating Token Index: 505

Text #18

Max Range: 0.8326. Min Range: -0.8326

Max Act: 0.3920. Min Act: -0.0000

Data Index: 949460 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 0.8326. Min Range: -0.8326

Max Act: 0.4179. Min Act: -0.0000

Data Index: 435713 (C4 (Web Text))

Max Activating Token Index: 129