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

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

Neuron 4646 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: 0.9035. Min Range: -0.9035

Max Act: 0.9035. Min Act: -0.0000

Data Index: 554973 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.8989. Min Act: -0.0000

Data Index: 1136310 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.8298. Min Act: -0.0000

Data Index: 791117 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.8154. Min Act: -0.0000

Data Index: 1074029 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.7488. Min Act: -0.0000

Data Index: 914040 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.7460. Min Act: -0.0000

Data Index: 802521 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.7131. Min Act: -0.0000

Data Index: 537857 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6428. Min Act: -0.0000

Data Index: 1179005 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.7505. Min Act: -0.0000

Data Index: 731462 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6747. Min Act: -0.0000

Data Index: 1127677 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6409. Min Act: -0.0000

Data Index: 1010808 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6728. Min Act: -0.0000

Data Index: 1272783 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6466. Min Act: -0.0000

Data Index: 1238900 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6268. Min Act: -0.0000

Data Index: 545061 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6127. Min Act: -0.0000

Data Index: 1263935 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6091. Min Act: -0.0000

Data Index: 1140668 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6489. Min Act: -0.0000

Data Index: 419159 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6367. Min Act: -0.0000

Data Index: 1232499 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6299. Min Act: -0.0000

Data Index: 681501 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6461. Min Act: -0.0000

Data Index: 1633281 (Python Code)

Max Activating Token Index: 59