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

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

Neuron 200 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2103. Min Range: -3.2103

Max Act: 3.2103. Min Act: -0.0000

Data Index: 505700 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 3.2103. Min Range: -3.2103

Max Act: 3.0985. Min Act: -0.0000

Data Index: 765072 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 3.2103. Min Range: -3.2103

Max Act: 2.9438. Min Act: -0.0000

Data Index: 62120 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 3.2103. Min Range: -3.2103

Max Act: 2.7375. Min Act: -0.0000

Data Index: 1242925 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 3.2103. Min Range: -3.2103

Max Act: 2.7456. Min Act: -0.0000

Data Index: 934497 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 3.2103. Min Range: -3.2103

Max Act: 2.8313. Min Act: -0.0000

Data Index: 1130726 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 3.2103. Min Range: -3.2103

Max Act: 2.9653. Min Act: -0.0000

Data Index: 901621 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 3.2103. Min Range: -3.2103

Max Act: 2.5357. Min Act: -0.0000

Data Index: 835075 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 3.2103. Min Range: -3.2103

Max Act: 2.3945. Min Act: -0.0000

Data Index: 997602 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 3.2103. Min Range: -3.2103

Max Act: 2.4712. Min Act: -0.0000

Data Index: 44917 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 3.2103. Min Range: -3.2103

Max Act: 2.7183. Min Act: -0.0000

Data Index: 1246950 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 3.2103. Min Range: -3.2103

Max Act: 2.5536. Min Act: -0.0000

Data Index: 252043 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 3.2103. Min Range: -3.2103

Max Act: 2.6701. Min Act: -0.0000

Data Index: 836923 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 3.2103. Min Range: -3.2103

Max Act: 2.7842. Min Act: -0.0000

Data Index: 723714 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 3.2103. Min Range: -3.2103

Max Act: 2.1594. Min Act: -0.0000

Data Index: 896863 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 3.2103. Min Range: -3.2103

Max Act: 2.4508. Min Act: -0.0000

Data Index: 1202346 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 3.2103. Min Range: -3.2103

Max Act: 2.3188. Min Act: -0.0000

Data Index: 13111 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 3.2103. Min Range: -3.2103

Max Act: 2.3042. Min Act: -0.0000

Data Index: 1209164 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 3.2103. Min Range: -3.2103

Max Act: 2.5317. Min Act: -0.0000

Data Index: 777499 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 3.2103. Min Range: -3.2103

Max Act: 2.3991. Min Act: -0.0000

Data Index: 807725 (C4 (Web Text))

Max Activating Token Index: 37