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

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

Neuron 4365 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0813. Min Range: -1.0813

Max Act: 1.0813. Min Act: -0.0000

Data Index: 77908 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.9428. Min Act: -0.0000

Data Index: 512213 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.7967. Min Act: -0.0000

Data Index: 501717 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.8155. Min Act: -0.0000

Data Index: 1089790 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.8175. Min Act: -0.0000

Data Index: 980438 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.8258. Min Act: -0.0000

Data Index: 1218957 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.7810. Min Act: -0.0000

Data Index: 828315 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.7287. Min Act: -0.0000

Data Index: 705177 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.7432. Min Act: -0.0000

Data Index: 1271339 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.7226. Min Act: -0.0000

Data Index: 659447 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.7162. Min Act: -0.0000

Data Index: 1262007 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.7137. Min Act: -0.0000

Data Index: 1346693 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.6758. Min Act: -0.0000

Data Index: 1298522 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.7029. Min Act: -0.0000

Data Index: 818775 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.6469. Min Act: -0.0000

Data Index: 562238 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.6663. Min Act: -0.0000

Data Index: 461938 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.6161. Min Act: -0.0000

Data Index: 14231 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.6514. Min Act: -0.0000

Data Index: 635526 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.7001. Min Act: -0.0000

Data Index: 668671 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.6711. Min Act: -0.0000

Data Index: 1015944 (C4 (Web Text))

Max Activating Token Index: 860