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

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

Neuron 4055 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: 1.4592. Min Range: -1.4592

Max Act: 1.4592. Min Act: -0.0000

Data Index: 309728 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.3334. Min Act: -0.0000

Data Index: 3217 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.0020. Min Act: -0.0000

Data Index: 1298892 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.0534. Min Act: -0.0000

Data Index: 1327238 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.0494. Min Act: -0.0000

Data Index: 156953 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.0266. Min Act: -0.0000

Data Index: 459474 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.0019. Min Act: -0.0000

Data Index: 988399 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.0091. Min Act: -0.0000

Data Index: 1329721 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 1.4592. Min Range: -1.4592

Max Act: 0.9955. Min Act: -0.0000

Data Index: 1093279 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 1.4592. Min Range: -1.4592

Max Act: 0.9320. Min Act: -0.0000

Data Index: 352208 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 1.4592. Min Range: -1.4592

Max Act: 0.9710. Min Act: -0.0000

Data Index: 607793 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 1.4592. Min Range: -1.4592

Max Act: 0.8850. Min Act: -0.0000

Data Index: 41203 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 1.4592. Min Range: -1.4592

Max Act: 0.9332. Min Act: -0.0000

Data Index: 790907 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 1.4592. Min Range: -1.4592

Max Act: 0.9729. Min Act: -0.0000

Data Index: 288272 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 1.4592. Min Range: -1.4592

Max Act: 0.9183. Min Act: -0.0000

Data Index: 1277416 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 1.4592. Min Range: -1.4592

Max Act: 0.8708. Min Act: -0.0000

Data Index: 1190975 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 1.4592. Min Range: -1.4592

Max Act: 0.9142. Min Act: -0.0000

Data Index: 382915 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 1.4592. Min Range: -1.4592

Max Act: 0.9008. Min Act: -0.0000

Data Index: 1002715 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 1.4592. Min Range: -1.4592

Max Act: 0.9047. Min Act: -0.0000

Data Index: 925689 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 1.4592. Min Range: -1.4592

Max Act: 0.8320. Min Act: -0.0000

Data Index: 951911 (C4 (Web Text))

Max Activating Token Index: 941