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

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

Neuron 336 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: 2.0219. Min Range: -2.0219

Max Act: 2.0219. Min Act: -0.0000

Data Index: 1043519 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.5249. Min Act: -0.0000

Data Index: 1323596 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.4183. Min Act: -0.0000

Data Index: 407573 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.5042. Min Act: -0.0000

Data Index: 1172095 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.4924. Min Act: -0.0000

Data Index: 1243696 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.4550. Min Act: -0.0000

Data Index: 771987 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.1996. Min Act: -0.0000

Data Index: 141606 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.3405. Min Act: -0.0000

Data Index: 660266 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.4147. Min Act: -0.0000

Data Index: 925638 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.2839. Min Act: -0.0000

Data Index: 456951 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.2612. Min Act: -0.0000

Data Index: 989594 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.2494. Min Act: -0.0000

Data Index: 1191638 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.2378. Min Act: -0.0000

Data Index: 1230070 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.1869. Min Act: -0.0000

Data Index: 877226 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.2306. Min Act: -0.0000

Data Index: 639777 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.1549. Min Act: -0.0000

Data Index: 745642 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.1536. Min Act: -0.0000

Data Index: 1080448 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.1407. Min Act: -0.0000

Data Index: 355361 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.1377. Min Act: -0.0000

Data Index: 349440 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.0932. Min Act: -0.0000

Data Index: 739513 (C4 (Web Text))

Max Activating Token Index: 615