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

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

Neuron 5007 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: 1.1287. Min Range: -1.1287

Max Act: 1.1287. Min Act: -0.0000

Data Index: 495663 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 1.1287. Min Range: -1.1287

Max Act: 0.9851. Min Act: -0.0000

Data Index: 131938 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 1.1287. Min Range: -1.1287

Max Act: 1.0272. Min Act: -0.0000

Data Index: 55998 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 1.1287. Min Range: -1.1287

Max Act: 1.0113. Min Act: -0.0000

Data Index: 44850 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 1.1287. Min Range: -1.1287

Max Act: 1.0557. Min Act: -0.0000

Data Index: 1169159 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 1.1287. Min Range: -1.1287

Max Act: 0.8005. Min Act: -0.0000

Data Index: 462275 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 1.1287. Min Range: -1.1287

Max Act: 0.9069. Min Act: -0.0000

Data Index: 364729 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 1.1287. Min Range: -1.1287

Max Act: 0.7971. Min Act: -0.0000

Data Index: 1048822 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 1.1287. Min Range: -1.1287

Max Act: 0.8131. Min Act: -0.0000

Data Index: 409128 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 1.1287. Min Range: -1.1287

Max Act: 0.7531. Min Act: -0.0000

Data Index: 881422 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 1.1287. Min Range: -1.1287

Max Act: 0.7591. Min Act: -0.0000

Data Index: 790988 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 1.1287. Min Range: -1.1287

Max Act: 0.7569. Min Act: -0.0000

Data Index: 427587 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 1.1287. Min Range: -1.1287

Max Act: 0.7213. Min Act: -0.0000

Data Index: 995373 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 1.1287. Min Range: -1.1287

Max Act: 0.6894. Min Act: -0.0000

Data Index: 114327 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 1.1287. Min Range: -1.1287

Max Act: 0.6802. Min Act: -0.0000

Data Index: 884755 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 1.1287. Min Range: -1.1287

Max Act: 0.7316. Min Act: -0.0000

Data Index: 959335 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 1.1287. Min Range: -1.1287

Max Act: 0.6666. Min Act: -0.0000

Data Index: 303433 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 1.1287. Min Range: -1.1287

Max Act: 0.6858. Min Act: -0.0000

Data Index: 224878 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 1.1287. Min Range: -1.1287

Max Act: 0.6901. Min Act: -0.0000

Data Index: 164541 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 1.1287. Min Range: -1.1287

Max Act: 0.6235. Min Act: -0.0000

Data Index: 314164 (C4 (Web Text))

Max Activating Token Index: 267