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

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

Neuron 3282 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.8425. Min Act: -0.0000

Data Index: 1134391 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.8329. Min Act: -0.0000

Data Index: 924313 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.7290. Min Act: -0.0000

Data Index: 90850 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.7033. Min Act: -0.0000

Data Index: 434448 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.7069. Min Act: -0.0000

Data Index: 557486 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.6973. Min Act: -0.0000

Data Index: 681478 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.7069. Min Act: -0.0000

Data Index: 304775 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.6348. Min Act: -0.0000

Data Index: 502811 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.5945. Min Act: -0.0000

Data Index: 580081 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.6158. Min Act: -0.0000

Data Index: 504056 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.6294. Min Act: -0.0000

Data Index: 226377 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.6483. Min Act: -0.0000

Data Index: 50191 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.6306. Min Act: -0.0000

Data Index: 340841 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.6458. Min Act: -0.0000

Data Index: 480512 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1272786 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.6143. Min Act: -0.0000

Data Index: 1185921 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.6105. Min Act: -0.0000

Data Index: 1045335 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.5891. Min Act: -0.0000

Data Index: 1126294 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.6134. Min Act: -0.0000

Data Index: 815791 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.5858. Min Act: -0.0000

Data Index: 719485 (C4 (Web Text))

Max Activating Token Index: 602