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

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

Neuron 2228 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: 0.6832. Min Range: -0.6832

Max Act: 0.6832. Min Act: -0.0000

Data Index: 557977 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5668. Min Act: -0.0001

Data Index: 1255159 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5404. Min Act: -0.0001

Data Index: 1327147 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.4675. Min Act: -0.0000

Data Index: 868235 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.4436. Min Act: -0.0001

Data Index: 995418 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.4030. Min Act: -0.0000

Data Index: 319751 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.4197. Min Act: -0.0000

Data Index: 708186 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.4175. Min Act: -0.0000

Data Index: 333853 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.3884. Min Act: -0.0000

Data Index: 1114920 (C4 (Web Text))

Max Activating Token Index: 542

Text #9

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.3851. Min Act: -0.0000

Data Index: 155795 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.3905. Min Act: -0.0000

Data Index: 475818 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.3788. Min Act: -0.0001

Data Index: 456993 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.3757. Min Act: -0.0000

Data Index: 473312 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.3715. Min Act: -0.0000

Data Index: 819220 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.3644. Min Act: -0.0000

Data Index: 451885 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.3392. Min Act: -0.0000

Data Index: 245968 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.3410. Min Act: -0.0000

Data Index: 1059548 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.3588. Min Act: -0.0000

Data Index: 119745 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.3398. Min Act: -0.0000

Data Index: 664242 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.3241. Min Act: -0.0000

Data Index: 682858 (C4 (Web Text))

Max Activating Token Index: 246