Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1537 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1502. Min Act: -0.0001

Data Index: 525673 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1239. Min Act: -0.0001

Data Index: 969859 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1305. Min Act: -0.0001

Data Index: 978445 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1344. Min Act: -0.0001

Data Index: 950534 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1298. Min Act: -0.0001

Data Index: 44091 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1261. Min Act: -0.0001

Data Index: 802091 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1185. Min Act: -0.0001

Data Index: 64381 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1280. Min Act: -0.0001

Data Index: 75519 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1340. Min Act: -0.0001

Data Index: 88455 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1201. Min Act: -0.0001

Data Index: 1180355 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1105. Min Act: -0.0001

Data Index: 1018231 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1368. Min Act: -0.0001

Data Index: 384869 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1216. Min Act: -0.0001

Data Index: 373778 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1174. Min Act: -0.0001

Data Index: 757269 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1069. Min Act: -0.0001

Data Index: 712449 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1160. Min Act: -0.0001

Data Index: 1029645 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1191. Min Act: -0.0001

Data Index: 904734 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1188. Min Act: -0.0001

Data Index: 958201 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1076. Min Act: -0.0001

Data Index: 738739 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1117. Min Act: -0.0001

Data Index: 322543 (C4 (Web Text))

Max Activating Token Index: 816