Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5078 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3270. Min Range: -1.3270

Max Act: 1.2797. Min Act: -0.0001

Data Index: 668921 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 1.3270. Min Range: -1.3270

Max Act: 1.2266. Min Act: -0.0001

Data Index: 355936 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 1.3270. Min Range: -1.3270

Max Act: 1.2679. Min Act: -0.0001

Data Index: 1116753 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 1.3270. Min Range: -1.3270

Max Act: 1.1671. Min Act: -0.0001

Data Index: 1120317 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 1.3270. Min Range: -1.3270

Max Act: 1.1905. Min Act: -0.0001

Data Index: 514745 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 1.3270. Min Range: -1.3270

Max Act: 1.1914. Min Act: -0.0001

Data Index: 1321240 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 1.3270. Min Range: -1.3270

Max Act: 1.3270. Min Act: -0.0001

Data Index: 252745 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 1.3270. Min Range: -1.3270

Max Act: 1.1047. Min Act: -0.0001

Data Index: 1136310 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 1.3270. Min Range: -1.3270

Max Act: 1.2134. Min Act: -0.0001

Data Index: 1156278 (C4 (Web Text))

Max Activating Token Index: 325

Text #9

Max Range: 1.3270. Min Range: -1.3270

Max Act: 1.1425. Min Act: -0.0001

Data Index: 1273140 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 1.3270. Min Range: -1.3270

Max Act: 1.1163. Min Act: -0.0001

Data Index: 1263297 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 1.3270. Min Range: -1.3270

Max Act: 1.1141. Min Act: -0.0001

Data Index: 524032 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 1.3270. Min Range: -1.3270

Max Act: 1.1825. Min Act: -0.0001

Data Index: 385107 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 1.3270. Min Range: -1.3270

Max Act: 1.1712. Min Act: -0.0001

Data Index: 196942 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 1.3270. Min Range: -1.3270

Max Act: 1.1035. Min Act: -0.0001

Data Index: 531425 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 1.3270. Min Range: -1.3270

Max Act: 1.1181. Min Act: -0.0001

Data Index: 191012 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 1.3270. Min Range: -1.3270

Max Act: 1.0944. Min Act: -0.0001

Data Index: 249220 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 1.3270. Min Range: -1.3270

Max Act: 1.0118. Min Act: -0.0001

Data Index: 917825 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 1.3270. Min Range: -1.3270

Max Act: 1.1088. Min Act: -0.0001

Data Index: 641943 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 1.3270. Min Range: -1.3270

Max Act: 1.0784. Min Act: -0.0001

Data Index: 32188 (C4 (Web Text))

Max Activating Token Index: 587