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

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

Neuron 228 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4211. Min Range: -0.4211

Max Act: 0.4211. Min Act: -0.0000

Data Index: 179172 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 0.4211. Min Range: -0.4211

Max Act: 0.3810. Min Act: -0.0000

Data Index: 151211 (C4 (Web Text))

Max Activating Token Index: 324

Text #2

Max Range: 0.4211. Min Range: -0.4211

Max Act: 0.3286. Min Act: -0.0000

Data Index: 1082933 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 0.4211. Min Range: -0.4211

Max Act: 0.3482. Min Act: -0.0000

Data Index: 532677 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 0.4211. Min Range: -0.4211

Max Act: 0.3383. Min Act: -0.0000

Data Index: 624739 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 0.4211. Min Range: -0.4211

Max Act: 0.3380. Min Act: -0.0000

Data Index: 1140321 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.4211. Min Range: -0.4211

Max Act: 0.3155. Min Act: -0.0000

Data Index: 696994 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 0.4211. Min Range: -0.4211

Max Act: 0.3309. Min Act: -0.0000

Data Index: 161127 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.4211. Min Range: -0.4211

Max Act: 0.3208. Min Act: -0.0000

Data Index: 1163615 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 0.4211. Min Range: -0.4211

Max Act: 0.3066. Min Act: -0.0000

Data Index: 876054 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 0.4211. Min Range: -0.4211

Max Act: 0.3146. Min Act: -0.0000

Data Index: 1581307 (Python Code)

Max Activating Token Index: 405

Text #11

Max Range: 0.4211. Min Range: -0.4211

Max Act: 0.3262. Min Act: -0.0000

Data Index: 192174 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 0.4211. Min Range: -0.4211

Max Act: 0.3043. Min Act: -0.0000

Data Index: 931491 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.4211. Min Range: -0.4211

Max Act: 0.2998. Min Act: -0.0000

Data Index: 1073639 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 0.4211. Min Range: -0.4211

Max Act: 0.3007. Min Act: -0.0000

Data Index: 1386623 (Python Code)

Max Activating Token Index: 234

Text #15

Max Range: 0.4211. Min Range: -0.4211

Max Act: 0.2848. Min Act: -0.0000

Data Index: 1074730 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 0.4211. Min Range: -0.4211

Max Act: 0.2706. Min Act: -0.0000

Data Index: 1612521 (Python Code)

Max Activating Token Index: 707

Text #17

Max Range: 0.4211. Min Range: -0.4211

Max Act: 0.2939. Min Act: -0.0000

Data Index: 861178 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 0.4211. Min Range: -0.4211

Max Act: 0.2951. Min Act: -0.0000

Data Index: 123027 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 0.4211. Min Range: -0.4211

Max Act: 0.2700. Min Act: -0.0000

Data Index: 1653162 (Python Code)

Max Activating Token Index: 113