Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2860 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.7888. Min Act: -0.0000

Data Index: 1127028 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.9232. Min Act: -0.0000

Data Index: 710964 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.6552. Min Act: -0.0000

Data Index: 934335 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.6658. Min Act: -0.0000

Data Index: 890064 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.7133. Min Act: -0.0000

Data Index: 1038040 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.5332. Min Act: -0.0001

Data Index: 94166 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.4848. Min Act: -0.0001

Data Index: 1271557 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.4572. Min Act: -0.0000

Data Index: 298050 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.4997. Min Act: -0.0000

Data Index: 1077656 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.4368. Min Act: -0.0000

Data Index: 332792 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.3227. Min Act: -0.0000

Data Index: 203143 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.4425. Min Act: -0.0000

Data Index: 358627 (C4 (Web Text))

Max Activating Token Index: 553

Text #12

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.4952. Min Act: -0.0000

Data Index: 760816 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.4947. Min Act: -0.0000

Data Index: 982395 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.4841. Min Act: -0.0001

Data Index: 53911 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.4219. Min Act: -0.0000

Data Index: 1319641 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.3720. Min Act: -0.0000

Data Index: 462716 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.4157. Min Act: -0.0000

Data Index: 647199 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.2858. Min Act: -0.0000

Data Index: 1107345 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.2062. Min Act: -0.0000

Data Index: 471913 (C4 (Web Text))

Max Activating Token Index: 649