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

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

Neuron 5445 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2946. Min Range: -2.2946

Max Act: 2.2946. Min Act: -0.0000

Data Index: 1300943 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 2.2946. Min Range: -2.2946

Max Act: 2.0745. Min Act: -0.0000

Data Index: 790043 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 2.2946. Min Range: -2.2946

Max Act: 2.1556. Min Act: -0.0000

Data Index: 425204 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 2.2946. Min Range: -2.2946

Max Act: 2.0132. Min Act: -0.0000

Data Index: 612834 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 2.2946. Min Range: -2.2946

Max Act: 2.0483. Min Act: -0.0000

Data Index: 1099548 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 2.2946. Min Range: -2.2946

Max Act: 1.9190. Min Act: -0.0000

Data Index: 893544 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 2.2946. Min Range: -2.2946

Max Act: 2.1365. Min Act: -0.0000

Data Index: 1260957 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 2.2946. Min Range: -2.2946

Max Act: 1.9515. Min Act: -0.0000

Data Index: 10408 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 2.2946. Min Range: -2.2946

Max Act: 1.8987. Min Act: -0.0000

Data Index: 345764 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 2.2946. Min Range: -2.2946

Max Act: 1.9005. Min Act: -0.0000

Data Index: 1338373 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 2.2946. Min Range: -2.2946

Max Act: 1.9593. Min Act: -0.0000

Data Index: 977483 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 2.2946. Min Range: -2.2946

Max Act: 1.7960. Min Act: -0.0000

Data Index: 91086 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 2.2946. Min Range: -2.2946

Max Act: 1.8577. Min Act: -0.0000

Data Index: 1049164 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 2.2946. Min Range: -2.2946

Max Act: 1.8467. Min Act: -0.0000

Data Index: 1140727 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 2.2946. Min Range: -2.2946

Max Act: 1.7401. Min Act: -0.0000

Data Index: 1147839 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 2.2946. Min Range: -2.2946

Max Act: 1.8264. Min Act: -0.0000

Data Index: 90103 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 2.2946. Min Range: -2.2946

Max Act: 1.7199. Min Act: -0.0000

Data Index: 585485 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 2.2946. Min Range: -2.2946

Max Act: 1.6967. Min Act: -0.0000

Data Index: 118697 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 2.2946. Min Range: -2.2946

Max Act: 1.7971. Min Act: -0.0000

Data Index: 1345107 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 2.2946. Min Range: -2.2946

Max Act: 1.7962. Min Act: -0.0000

Data Index: 459429 (C4 (Web Text))

Max Activating Token Index: 620