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

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

Neuron 510 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.9980. Min Act: -0.0004

Data Index: 388190 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8695. Min Act: -0.0004

Data Index: 555086 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8427. Min Act: -0.0004

Data Index: 902609 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8069. Min Act: -0.0004

Data Index: 401648 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7900. Min Act: -0.0004

Data Index: 1082178 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.6957. Min Act: -0.0004

Data Index: 1288260 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7514. Min Act: -0.0004

Data Index: 747228 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7186. Min Act: -0.0004

Data Index: 1136299 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7503. Min Act: -0.0004

Data Index: 76278 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7305. Min Act: -0.0004

Data Index: 44395 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7239. Min Act: -0.0004

Data Index: 985844 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7532. Min Act: -0.0004

Data Index: 181035 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7163. Min Act: -0.0004

Data Index: 1038152 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7440. Min Act: -0.0004

Data Index: 226269 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.6707. Min Act: -0.0004

Data Index: 929245 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.6260. Min Act: -0.0004

Data Index: 1229111 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7365. Min Act: -0.0004

Data Index: 472145 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.6306. Min Act: -0.0004

Data Index: 744699 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7020. Min Act: -0.0004

Data Index: 905619 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.6583. Min Act: -0.0004

Data Index: 1359015 (C4 (Web Text))

Max Activating Token Index: 898