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

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

Neuron 734 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: 0.4376. Min Range: -0.4376

Max Act: 0.4376. Min Act: -0.0001

Data Index: 1097532 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3919. Min Act: -0.0001

Data Index: 951501 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3668. Min Act: -0.0001

Data Index: 249544 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3329. Min Act: -0.0001

Data Index: 1204741 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3295. Min Act: -0.0001

Data Index: 711159 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3297. Min Act: -0.0001

Data Index: 146204 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3282. Min Act: -0.0001

Data Index: 679434 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3243. Min Act: -0.0001

Data Index: 967315 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3210. Min Act: -0.0001

Data Index: 1175061 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3228. Min Act: -0.0001

Data Index: 366972 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3148. Min Act: -0.0001

Data Index: 481280 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3027. Min Act: -0.0001

Data Index: 1231848 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3043. Min Act: -0.0001

Data Index: 1173358 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3068. Min Act: -0.0001

Data Index: 704863 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3051. Min Act: -0.0001

Data Index: 377991 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3070. Min Act: -0.0001

Data Index: 1176235 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3200. Min Act: -0.0001

Data Index: 552344 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3138. Min Act: -0.0001

Data Index: 123045 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3114. Min Act: -0.0001

Data Index: 982720 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3085. Min Act: -0.0001

Data Index: 342782 (C4 (Web Text))

Max Activating Token Index: 483