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

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

Neuron 464 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.5480. Min Act: -0.0001

Data Index: 947830 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.5311. Min Act: -0.0001

Data Index: 1305274 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.5231. Min Act: -0.0001

Data Index: 869809 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.5177. Min Act: -0.0001

Data Index: 59935 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4946. Min Act: -0.0001

Data Index: 1007270 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4868. Min Act: -0.0001

Data Index: 1070677 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4218. Min Act: -0.0001

Data Index: 1350949 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.5038. Min Act: -0.0001

Data Index: 1017807 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4731. Min Act: -0.0001

Data Index: 1124135 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4392. Min Act: -0.0001

Data Index: 73756 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4520. Min Act: -0.0001

Data Index: 1009044 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4667. Min Act: -0.0001

Data Index: 87571 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4495. Min Act: -0.0001

Data Index: 1132583 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4653. Min Act: -0.0001

Data Index: 227002 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4706. Min Act: -0.0001

Data Index: 847954 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4721. Min Act: -0.0001

Data Index: 764219 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4553. Min Act: -0.0001

Data Index: 1089749 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4663. Min Act: -0.0001

Data Index: 1216282 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4808. Min Act: -0.0001

Data Index: 225277 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4877. Min Act: -0.0001

Data Index: 155213 (C4 (Web Text))

Max Activating Token Index: 853