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

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

Neuron 4423 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0296. Min Act: -0.0001

Data Index: 1292527 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0274. Min Act: -0.0001

Data Index: 149709 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0261. Min Act: -0.0001

Data Index: 669220 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0250. Min Act: -0.0001

Data Index: 1063295 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0250. Min Act: -0.0001

Data Index: 1158631 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0249. Min Act: -0.0001

Data Index: 709353 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0239. Min Act: -0.0001

Data Index: 13118 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0237. Min Act: -0.0001

Data Index: 1225976 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0232. Min Act: -0.0001

Data Index: 759022 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0233. Min Act: -0.0001

Data Index: 643123 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0232. Min Act: -0.0001

Data Index: 893654 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0233. Min Act: -0.0001

Data Index: 508264 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0230. Min Act: -0.0002

Data Index: 567705 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0227. Min Act: -0.0001

Data Index: 371127 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0227. Min Act: -0.0001

Data Index: 1079300 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0225. Min Act: -0.0001

Data Index: 975294 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0223. Min Act: -0.0001

Data Index: 175810 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0223. Min Act: -0.0001

Data Index: 1246862 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0223. Min Act: -0.0001

Data Index: 879187 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0226. Min Act: -0.0001

Data Index: 665042 (C4 (Web Text))

Max Activating Token Index: 231