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

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

Neuron 4501 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3020. Min Range: -4.3020

Max Act: 4.3020. Min Act: -0.0000

Data Index: 1178896 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 4.3020. Min Range: -4.3020

Max Act: 4.2592. Min Act: -0.0000

Data Index: 1363237 (Python Code)

Max Activating Token Index: 902

Text #2

Max Range: 4.3020. Min Range: -4.3020

Max Act: 3.7281. Min Act: -0.0000

Data Index: 986913 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 4.3020. Min Range: -4.3020

Max Act: 3.4411. Min Act: -0.0000

Data Index: 569321 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 4.3020. Min Range: -4.3020

Max Act: 3.3985. Min Act: -0.0000

Data Index: 666887 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 4.3020. Min Range: -4.3020

Max Act: 3.3226. Min Act: -0.0000

Data Index: 169402 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 4.3020. Min Range: -4.3020

Max Act: 3.1324. Min Act: -0.0000

Data Index: 922308 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 4.3020. Min Range: -4.3020

Max Act: 3.2955. Min Act: -0.0000

Data Index: 559258 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 4.3020. Min Range: -4.3020

Max Act: 3.2207. Min Act: -0.0000

Data Index: 172812 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 4.3020. Min Range: -4.3020

Max Act: 3.2274. Min Act: -0.0000

Data Index: 1113120 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 4.3020. Min Range: -4.3020

Max Act: 3.0825. Min Act: -0.0000

Data Index: 745273 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 4.3020. Min Range: -4.3020

Max Act: 2.8883. Min Act: -0.0000

Data Index: 907270 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 4.3020. Min Range: -4.3020

Max Act: 3.0434. Min Act: -0.0000

Data Index: 1213014 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 4.3020. Min Range: -4.3020

Max Act: 3.0301. Min Act: 0.0000

Data Index: 1011107 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 4.3020. Min Range: -4.3020

Max Act: 3.0040. Min Act: -0.0000

Data Index: 715088 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 4.3020. Min Range: -4.3020

Max Act: 3.0253. Min Act: -0.0000

Data Index: 516678 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 4.3020. Min Range: -4.3020

Max Act: 2.9956. Min Act: -0.0000

Data Index: 325152 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 4.3020. Min Range: -4.3020

Max Act: 2.9665. Min Act: -0.0000

Data Index: 453745 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 4.3020. Min Range: -4.3020

Max Act: 2.9550. Min Act: -0.0000

Data Index: 46776 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 4.3020. Min Range: -4.3020

Max Act: 2.9489. Min Act: -0.0000

Data Index: 930695 (C4 (Web Text))

Max Activating Token Index: 944