Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 882 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.5754. Min Act: -0.0000

Data Index: 80415 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.5113. Min Act: -0.0001

Data Index: 202729 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.4623. Min Act: -0.0001

Data Index: 318238 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.4402. Min Act: -0.0001

Data Index: 136378 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.4085. Min Act: -0.0001

Data Index: 951612 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.4199. Min Act: -0.0001

Data Index: 240684 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.4299. Min Act: -0.0001

Data Index: 920474 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.4141. Min Act: -0.0001

Data Index: 201922 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.3946. Min Act: -0.0001

Data Index: 236333 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.4641. Min Act: -0.0001

Data Index: 617907 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.4208. Min Act: -0.0001

Data Index: 696445 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.4113. Min Act: -0.0001

Data Index: 64093 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.4054. Min Act: -0.0001

Data Index: 293283 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.4186. Min Act: -0.0000

Data Index: 1114978 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.3885. Min Act: -0.0000

Data Index: 336723 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.3816. Min Act: -0.0001

Data Index: 1270758 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.3975. Min Act: -0.0001

Data Index: 146329 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.3951. Min Act: -0.0001

Data Index: 809405 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.3689. Min Act: -0.0001

Data Index: 853937 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.3796. Min Act: -0.0001

Data Index: 286761 (C4 (Web Text))

Max Activating Token Index: 286