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

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

Neuron 5632 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.4854. Min Act: -0.0000

Data Index: 1309549 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.2600. Min Act: -0.0000

Data Index: 936318 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.3308. Min Act: -0.0000

Data Index: 154523 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.1274. Min Act: -0.0000

Data Index: 368746 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.1170. Min Act: -0.0000

Data Index: 1284652 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.1114. Min Act: -0.0000

Data Index: 1189107 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.1201. Min Act: -0.0000

Data Index: 753492 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.0355. Min Act: -0.0000

Data Index: 1531144 (Python Code)

Max Activating Token Index: 146

Text #8

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.0878. Min Act: -0.0000

Data Index: 1619726 (Python Code)

Max Activating Token Index: 503

Text #9

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.0851. Min Act: -0.0000

Data Index: 1170170 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.1410. Min Act: -0.0000

Data Index: 719574 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.0934. Min Act: -0.0000

Data Index: 1274042 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.0546. Min Act: -0.0000

Data Index: 949293 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.0524. Min Act: -0.0000

Data Index: 261996 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.0983. Min Act: -0.0000

Data Index: 805202 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 1.4854. Min Range: -1.4854

Max Act: 0.9934. Min Act: -0.0000

Data Index: 1627810 (Python Code)

Max Activating Token Index: 946

Text #16

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.0117. Min Act: -0.0000

Data Index: 812773 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 1.4854. Min Range: -1.4854

Max Act: 1.0103. Min Act: -0.0000

Data Index: 1228246 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 1.4854. Min Range: -1.4854

Max Act: 0.9942. Min Act: -0.0000

Data Index: 376777 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 1.4854. Min Range: -1.4854

Max Act: 0.9565. Min Act: -0.0000

Data Index: 1632304 (Python Code)

Max Activating Token Index: 786