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

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

Neuron 550 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.7764. Min Act: -0.0000

Data Index: 237675 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.6806. Min Act: -0.0000

Data Index: 952742 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.7237. Min Act: -0.0000

Data Index: 1289434 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.6486. Min Act: -0.0000

Data Index: 16595 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.6272. Min Act: -0.0000

Data Index: 54990 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.6447. Min Act: -0.0000

Data Index: 883262 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.6408. Min Act: -0.0000

Data Index: 1000247 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.6402. Min Act: -0.0000

Data Index: 97925 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.6242. Min Act: -0.0000

Data Index: 1342902 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.6070. Min Act: -0.0000

Data Index: 447774 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.5996. Min Act: -0.0000

Data Index: 587370 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.6098. Min Act: -0.0000

Data Index: 1242584 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.5946. Min Act: -0.0000

Data Index: 841610 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.5925. Min Act: -0.0000

Data Index: 1290686 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.5714. Min Act: -0.0000

Data Index: 733457 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.5694. Min Act: -0.0000

Data Index: 815413 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.5613. Min Act: -0.0000

Data Index: 527485 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.6293. Min Act: -0.0000

Data Index: 1301432 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.5774. Min Act: -0.0000

Data Index: 787156 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.5849. Min Act: -0.0000

Data Index: 1070268 (C4 (Web Text))

Max Activating Token Index: 195