Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3872 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.1505. Min Range: -3.1505

Max Act: 3.1505. Min Act: -0.0001

Data Index: 221521 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 3.1505. Min Range: -3.1505

Max Act: 2.8479. Min Act: -0.0001

Data Index: 892093 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 3.1505. Min Range: -3.1505

Max Act: 2.7370. Min Act: -0.0001

Data Index: 744937 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 3.1505. Min Range: -3.1505

Max Act: 2.3907. Min Act: -0.0001

Data Index: 259063 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 3.1505. Min Range: -3.1505

Max Act: 2.5733. Min Act: -0.0001

Data Index: 1214669 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 3.1505. Min Range: -3.1505

Max Act: 2.1837. Min Act: -0.0001

Data Index: 1251593 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 3.1505. Min Range: -3.1505

Max Act: 2.5566. Min Act: -0.0001

Data Index: 673963 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 3.1505. Min Range: -3.1505

Max Act: 2.1936. Min Act: -0.0001

Data Index: 347598 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 3.1505. Min Range: -3.1505

Max Act: 1.7061. Min Act: -0.0001

Data Index: 368912 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 3.1505. Min Range: -3.1505

Max Act: 1.9258. Min Act: -0.0001

Data Index: 1047384 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 3.1505. Min Range: -3.1505

Max Act: 1.5349. Min Act: -0.0001

Data Index: 190050 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 3.1505. Min Range: -3.1505

Max Act: 2.0549. Min Act: -0.0001

Data Index: 420626 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 3.1505. Min Range: -3.1505

Max Act: 1.9137. Min Act: -0.0001

Data Index: 1343866 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 3.1505. Min Range: -3.1505

Max Act: 1.8689. Min Act: -0.0001

Data Index: 264583 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 3.1505. Min Range: -3.1505

Max Act: 1.7183. Min Act: -0.0001

Data Index: 437391 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 3.1505. Min Range: -3.1505

Max Act: 1.7140. Min Act: -0.0001

Data Index: 1345182 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 3.1505. Min Range: -3.1505

Max Act: 2.1415. Min Act: -0.0001

Data Index: 202992 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 3.1505. Min Range: -3.1505

Max Act: 1.8750. Min Act: -0.0001

Data Index: 1054911 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 3.1505. Min Range: -3.1505

Max Act: 1.9416. Min Act: -0.0001

Data Index: 585082 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 3.1505. Min Range: -3.1505

Max Act: 1.9244. Min Act: -0.0001

Data Index: 578236 (C4 (Web Text))

Max Activating Token Index: 919