Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4085 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.7278. Min Act: 0.0000

Data Index: 980563 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5315. Min Act: -0.0000

Data Index: 1270488 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4965. Min Act: 0.0000

Data Index: 321362 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5434. Min Act: -0.0000

Data Index: 540214 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5012. Min Act: -0.0000

Data Index: 1235082 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5016. Min Act: -0.0000

Data Index: 131494 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4840. Min Act: 0.0000

Data Index: 689526 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4787. Min Act: -0.0000

Data Index: 1343385 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4627. Min Act: -0.0000

Data Index: 593864 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4491. Min Act: -0.0000

Data Index: 732209 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4447. Min Act: -0.0000

Data Index: 432630 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4317. Min Act: -0.0000

Data Index: 738819 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4197. Min Act: -0.0000

Data Index: 904944 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4457. Min Act: -0.0000

Data Index: 18023 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4563. Min Act: -0.0000

Data Index: 1132206 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4414. Min Act: -0.0000

Data Index: 675068 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4423. Min Act: -0.0000

Data Index: 983508 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4691. Min Act: -0.0000

Data Index: 1184248 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4244. Min Act: -0.0000

Data Index: 65241 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4668. Min Act: -0.0000

Data Index: 1164234 (C4 (Web Text))

Max Activating Token Index: 159