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

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

Neuron 5051 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1271. Min Act: -0.0002

Data Index: 1187572 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1209. Min Act: -0.0002

Data Index: 1302099 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1159. Min Act: -0.0002

Data Index: 308304 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1139. Min Act: -0.0002

Data Index: 568048 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1115. Min Act: -0.0002

Data Index: 349264 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1157. Min Act: -0.0002

Data Index: 717108 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1073. Min Act: -0.0002

Data Index: 359391 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1062. Min Act: -0.0002

Data Index: 978030 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1034. Min Act: -0.0002

Data Index: 689419 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0992. Min Act: -0.0002

Data Index: 992557 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0955. Min Act: -0.0002

Data Index: 1156709 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0953. Min Act: -0.0002

Data Index: 368320 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1032. Min Act: -0.0002

Data Index: 1324145 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0989. Min Act: -0.0002

Data Index: 459393 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0994. Min Act: -0.0002

Data Index: 460111 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0944. Min Act: -0.0002

Data Index: 1208880 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1015. Min Act: -0.0002

Data Index: 737896 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0970. Min Act: -0.0002

Data Index: 542501 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0936. Min Act: -0.0002

Data Index: 117950 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0965. Min Act: -0.0002

Data Index: 754450 (C4 (Web Text))

Max Activating Token Index: 718