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

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

Neuron 2786 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.6408. Min Range: -7.6408

Max Act: 7.6408. Min Act: -0.0000

Data Index: 1148267 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 7.6408. Min Range: -7.6408

Max Act: 7.3193. Min Act: -0.0000

Data Index: 393271 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 7.6408. Min Range: -7.6408

Max Act: 7.4613. Min Act: -0.0000

Data Index: 384268 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 7.6408. Min Range: -7.6408

Max Act: 7.4411. Min Act: -0.0000

Data Index: 470447 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 7.6408. Min Range: -7.6408

Max Act: 7.4417. Min Act: -0.0000

Data Index: 711465 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 7.6408. Min Range: -7.6408

Max Act: 6.7717. Min Act: -0.0000

Data Index: 705948 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 7.6408. Min Range: -7.6408

Max Act: 6.7345. Min Act: -0.0000

Data Index: 940167 (C4 (Web Text))

Max Activating Token Index: 521

Text #7

Max Range: 7.6408. Min Range: -7.6408

Max Act: 6.7001. Min Act: -0.0000

Data Index: 302216 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 7.6408. Min Range: -7.6408

Max Act: 6.6789. Min Act: -0.0000

Data Index: 475887 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 7.6408. Min Range: -7.6408

Max Act: 6.6398. Min Act: -0.0000

Data Index: 263646 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 7.6408. Min Range: -7.6408

Max Act: 6.4475. Min Act: -0.0000

Data Index: 1161251 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 7.6408. Min Range: -7.6408

Max Act: 6.2262. Min Act: -0.0000

Data Index: 1084423 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 7.6408. Min Range: -7.6408

Max Act: 6.5620. Min Act: -0.0000

Data Index: 385692 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 7.6408. Min Range: -7.6408

Max Act: 6.3677. Min Act: -0.0000

Data Index: 233264 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 7.6408. Min Range: -7.6408

Max Act: 6.5243. Min Act: -0.0000

Data Index: 1022667 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 7.6408. Min Range: -7.6408

Max Act: 6.2640. Min Act: -0.0000

Data Index: 407897 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 7.6408. Min Range: -7.6408

Max Act: 6.4324. Min Act: -0.0000

Data Index: 278407 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 7.6408. Min Range: -7.6408

Max Act: 6.6247. Min Act: -0.0000

Data Index: 746603 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 7.6408. Min Range: -7.6408

Max Act: 6.4057. Min Act: -0.0000

Data Index: 1304666 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 7.6408. Min Range: -7.6408

Max Act: 6.1650. Min Act: -0.0000

Data Index: 1018047 (C4 (Web Text))

Max Activating Token Index: 941