Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 98 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.5591. Min Act: -0.0000

Data Index: 474606 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.5236. Min Act: -0.0000

Data Index: 881458 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4771. Min Act: -0.0000

Data Index: 38921 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4819. Min Act: -0.0000

Data Index: 888786 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4808. Min Act: -0.0000

Data Index: 518582 (C4 (Web Text))

Max Activating Token Index: 1015

Text #5

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.5006. Min Act: -0.0000

Data Index: 271486 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4642. Min Act: -0.0000

Data Index: 1586244 (Python Code)

Max Activating Token Index: 151

Text #7

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4574. Min Act: -0.0000

Data Index: 457160 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.5176. Min Act: -0.0000

Data Index: 197450 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4321. Min Act: -0.0000

Data Index: 974280 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4457. Min Act: -0.0000

Data Index: 1174811 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.5163. Min Act: -0.0000

Data Index: 806534 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4475. Min Act: -0.0000

Data Index: 1234247 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4311. Min Act: -0.0000

Data Index: 485420 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4502. Min Act: -0.0000

Data Index: 729952 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4202. Min Act: -0.0000

Data Index: 562947 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.3826. Min Act: -0.0000

Data Index: 678043 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.3844. Min Act: -0.0000

Data Index: 90161 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.3474. Min Act: -0.0000

Data Index: 1416867 (Python Code)

Max Activating Token Index: 541

Text #19

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.3456. Min Act: -0.0000

Data Index: 61117 (C4 (Web Text))

Max Activating Token Index: 95