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

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

Neuron 3344 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.4405. Min Act: -0.0001

Data Index: 52955 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.4410. Min Act: -0.0000

Data Index: 712094 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.4188. Min Act: -0.0001

Data Index: 1280826 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.4051. Min Act: -0.0000

Data Index: 951130 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.4034. Min Act: -0.0001

Data Index: 1400739 (Python Code)

Max Activating Token Index: 157

Text #5

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.4022. Min Act: -0.0001

Data Index: 1532551 (Python Code)

Max Activating Token Index: 340

Text #6

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.4003. Min Act: -0.0001

Data Index: 624874 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.3821. Min Act: -0.0000

Data Index: 542188 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.3823. Min Act: -0.0000

Data Index: 91723 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.3842. Min Act: -0.0000

Data Index: 953556 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.3660. Min Act: -0.0000

Data Index: 109416 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.3710. Min Act: -0.0000

Data Index: 5692 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.3574. Min Act: -0.0000

Data Index: 36021 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.3597. Min Act: -0.0000

Data Index: 463364 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.3707. Min Act: -0.0001

Data Index: 459329 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.3679. Min Act: -0.0001

Data Index: 1560199 (Python Code)

Max Activating Token Index: 504

Text #16

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.3677. Min Act: -0.0000

Data Index: 982289 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.3553. Min Act: -0.0000

Data Index: 227286 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.3540. Min Act: -0.0001

Data Index: 229185 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.3683. Min Act: -0.0000

Data Index: 959932 (C4 (Web Text))

Max Activating Token Index: 356