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

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

Neuron 3989 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.5061. Min Act: -0.0000

Data Index: 82136 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.4669. Min Act: -0.0000

Data Index: 82215 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.4838. Min Act: -0.0000

Data Index: 219529 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.5088. Min Act: -0.0000

Data Index: 1139257 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.4982. Min Act: -0.0000

Data Index: 1319827 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.4645. Min Act: -0.0000

Data Index: 966342 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.5077. Min Act: -0.0000

Data Index: 1236236 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.5073. Min Act: -0.0000

Data Index: 777762 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.4869. Min Act: -0.0000

Data Index: 76429 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.4801. Min Act: -0.0000

Data Index: 674123 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.4802. Min Act: -0.0000

Data Index: 532055 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.4321. Min Act: -0.0000

Data Index: 509908 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.4813. Min Act: -0.0000

Data Index: 1089501 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.4482. Min Act: -0.0000

Data Index: 1006108 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.4480. Min Act: -0.0000

Data Index: 257816 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.4167. Min Act: -0.0000

Data Index: 1027614 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.4010. Min Act: -0.0000

Data Index: 280123 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.4312. Min Act: -0.0000

Data Index: 536011 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.4304. Min Act: -0.0000

Data Index: 1041098 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.4020. Min Act: -0.0000

Data Index: 1215085 (C4 (Web Text))

Max Activating Token Index: 838