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

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

Neuron 1654 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1286. Min Act: -0.0001

Data Index: 727338 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1124. Min Act: -0.0001

Data Index: 763844 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1073. Min Act: -0.0001

Data Index: 1131001 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1065. Min Act: -0.0001

Data Index: 639823 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1047. Min Act: -0.0001

Data Index: 840548 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.0926. Min Act: -0.0001

Data Index: 141847 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1040. Min Act: -0.0001

Data Index: 819448 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.0991. Min Act: -0.0001

Data Index: 214704 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.0996. Min Act: -0.0001

Data Index: 557744 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.0946. Min Act: -0.0001

Data Index: 224258 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.0939. Min Act: -0.0001

Data Index: 1208057 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.0937. Min Act: -0.0001

Data Index: 11309 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.0966. Min Act: -0.0001

Data Index: 683245 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.0953. Min Act: -0.0001

Data Index: 606871 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.0923. Min Act: -0.0001

Data Index: 1045642 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.0939. Min Act: -0.0001

Data Index: 25796 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.0902. Min Act: -0.0001

Data Index: 284142 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.0903. Min Act: -0.0001

Data Index: 902310 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.0921. Min Act: -0.0001

Data Index: 720259 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.0913. Min Act: -0.0001

Data Index: 1162907 (C4 (Web Text))

Max Activating Token Index: 790