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

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

Neuron 5778 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: 0.7005. Min Range: -0.7005

Max Act: 0.7005. Min Act: 0.0001

Data Index: 824512 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.5505. Min Act: -0.0000

Data Index: 446945 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.5371. Min Act: -0.0000

Data Index: 179843 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.5104. Min Act: -0.0000

Data Index: 288083 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.5075. Min Act: -0.0000

Data Index: 1142269 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.5069. Min Act: -0.0000

Data Index: 852314 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.4891. Min Act: -0.0000

Data Index: 675381 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.4487. Min Act: -0.0000

Data Index: 594580 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.4572. Min Act: -0.0000

Data Index: 668235 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.4724. Min Act: -0.0000

Data Index: 763171 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.4155. Min Act: -0.0000

Data Index: 1028431 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.4350. Min Act: -0.0000

Data Index: 794415 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.4452. Min Act: -0.0000

Data Index: 1254025 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.4175. Min Act: -0.0000

Data Index: 802306 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.4404. Min Act: -0.0000

Data Index: 321567 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.4582. Min Act: -0.0000

Data Index: 1270003 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.4331. Min Act: -0.0000

Data Index: 592287 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.4183. Min Act: -0.0000

Data Index: 647047 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.4266. Min Act: -0.0000

Data Index: 170168 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.4091. Min Act: -0.0000

Data Index: 779626 (C4 (Web Text))

Max Activating Token Index: 1011