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

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

Neuron 1305 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.4409. Min Act: -0.0001

Data Index: 1342674 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.4607. Min Act: -0.0001

Data Index: 144319 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.4748. Min Act: -0.0001

Data Index: 380944 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.4506. Min Act: -0.0001

Data Index: 836980 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.4163. Min Act: -0.0001

Data Index: 1087654 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.4020. Min Act: -0.0001

Data Index: 226663 (C4 (Web Text))

Max Activating Token Index: 894

Text #6

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.4138. Min Act: -0.0001

Data Index: 127078 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.4017. Min Act: -0.0001

Data Index: 964119 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3785. Min Act: -0.0001

Data Index: 916383 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3933. Min Act: -0.0001

Data Index: 1181746 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3479. Min Act: -0.0001

Data Index: 498136 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3677. Min Act: -0.0001

Data Index: 18235 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3707. Min Act: -0.0001

Data Index: 660269 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3879. Min Act: -0.0001

Data Index: 461773 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3493. Min Act: -0.0001

Data Index: 690143 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3619. Min Act: -0.0001

Data Index: 1294521 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3603. Min Act: -0.0001

Data Index: 833867 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3639. Min Act: -0.0001

Data Index: 191973 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3927. Min Act: -0.0001

Data Index: 575309 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3854. Min Act: -0.0001

Data Index: 854385 (C4 (Web Text))

Max Activating Token Index: 651