Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 294 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.6226. Min Act: -0.0001

Data Index: 787452 (C4 (Web Text))

Max Activating Token Index: 982

Text #1

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.6135. Min Act: -0.0001

Data Index: 979232 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.6074. Min Act: -0.0001

Data Index: 1095096 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5655. Min Act: -0.0001

Data Index: 378440 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5791. Min Act: -0.0001

Data Index: 399943 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5591. Min Act: -0.0001

Data Index: 1290099 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5353. Min Act: -0.0001

Data Index: 1037139 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5254. Min Act: -0.0001

Data Index: 953300 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5242. Min Act: -0.0001

Data Index: 436434 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5604. Min Act: -0.0001

Data Index: 34280 (C4 (Web Text))

Max Activating Token Index: 374

Text #10

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5131. Min Act: -0.0001

Data Index: 430595 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5130. Min Act: -0.0001

Data Index: 1330283 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4939. Min Act: -0.0001

Data Index: 997130 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5187. Min Act: -0.0001

Data Index: 701400 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5014. Min Act: -0.0001

Data Index: 624097 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4983. Min Act: -0.0001

Data Index: 674109 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5201. Min Act: -0.0001

Data Index: 849987 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4942. Min Act: -0.0001

Data Index: 283490 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4745. Min Act: -0.0001

Data Index: 1252294 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4904. Min Act: -0.0001

Data Index: 578044 (C4 (Web Text))

Max Activating Token Index: 151