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

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

Neuron 902 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: 2.4740. Min Range: -2.4740

Max Act: 2.4692. Min Act: -0.0000

Data Index: 737201 (C4 (Web Text))

Max Activating Token Index: 995

Text #1

Max Range: 2.4740. Min Range: -2.4740

Max Act: 2.3777. Min Act: -0.0000

Data Index: 919544 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 2.4740. Min Range: -2.4740

Max Act: 2.4212. Min Act: -0.0000

Data Index: 811257 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 2.4740. Min Range: -2.4740

Max Act: 2.4740. Min Act: -0.0000

Data Index: 88942 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 2.4740. Min Range: -2.4740

Max Act: 2.3277. Min Act: -0.0000

Data Index: 1287090 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 2.4740. Min Range: -2.4740

Max Act: 2.2798. Min Act: -0.0000

Data Index: 1006199 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 2.4740. Min Range: -2.4740

Max Act: 2.3456. Min Act: -0.0000

Data Index: 26712 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 2.4740. Min Range: -2.4740

Max Act: 2.1377. Min Act: -0.0000

Data Index: 1133435 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 2.4740. Min Range: -2.4740

Max Act: 2.0827. Min Act: -0.0000

Data Index: 329016 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 2.4740. Min Range: -2.4740

Max Act: 1.9423. Min Act: -0.0000

Data Index: 36355 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 2.4740. Min Range: -2.4740

Max Act: 2.0107. Min Act: -0.0000

Data Index: 1013332 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 2.4740. Min Range: -2.4740

Max Act: 1.9929. Min Act: -0.0000

Data Index: 1025290 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 2.4740. Min Range: -2.4740

Max Act: 2.0698. Min Act: -0.0000

Data Index: 1145189 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 2.4740. Min Range: -2.4740

Max Act: 2.0435. Min Act: -0.0000

Data Index: 230066 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 2.4740. Min Range: -2.4740

Max Act: 1.9382. Min Act: -0.0000

Data Index: 842004 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 2.4740. Min Range: -2.4740

Max Act: 1.9343. Min Act: -0.0000

Data Index: 416374 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 2.4740. Min Range: -2.4740

Max Act: 2.0321. Min Act: -0.0000

Data Index: 124693 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 2.4740. Min Range: -2.4740

Max Act: 1.8691. Min Act: -0.0000

Data Index: 882977 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 2.4740. Min Range: -2.4740

Max Act: 1.7348. Min Act: -0.0000

Data Index: 1222716 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 2.4740. Min Range: -2.4740

Max Act: 1.8440. Min Act: -0.0000

Data Index: 696782 (C4 (Web Text))

Max Activating Token Index: 305