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

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

Neuron 1006 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: 0.4483. Min Range: -0.4483

Max Act: 0.4314. Min Act: -0.0000

Data Index: 1350108 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.4455. Min Act: -0.0000

Data Index: 1232609 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.4483. Min Act: -0.0000

Data Index: 1032755 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3759. Min Act: -0.0000

Data Index: 668303 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3683. Min Act: -0.0000

Data Index: 282297 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3422. Min Act: -0.0000

Data Index: 883869 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3484. Min Act: -0.0000

Data Index: 427232 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3293. Min Act: -0.0000

Data Index: 1046593 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3248. Min Act: -0.0000

Data Index: 516273 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3303. Min Act: -0.0000

Data Index: 141847 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3050. Min Act: -0.0000

Data Index: 709239 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3108. Min Act: -0.0000

Data Index: 936411 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3107. Min Act: -0.0000

Data Index: 788181 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3073. Min Act: -0.0000

Data Index: 994397 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.2844. Min Act: -0.0000

Data Index: 497066 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.2812. Min Act: -0.0000

Data Index: 840613 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.2592. Min Act: -0.0000

Data Index: 1336345 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.2742. Min Act: -0.0000

Data Index: 708364 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.2739. Min Act: -0.0000

Data Index: 425743 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.2805. Min Act: -0.0000

Data Index: 278633 (C4 (Web Text))

Max Activating Token Index: 102