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

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

Neuron 29 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1978. Min Range: -2.1978

Max Act: 2.1978. Min Act: -0.0000

Data Index: 1029501 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 2.1978. Min Range: -2.1978

Max Act: 2.0904. Min Act: -0.0000

Data Index: 311865 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 2.1978. Min Range: -2.1978

Max Act: 2.0512. Min Act: -0.0000

Data Index: 405127 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 2.1978. Min Range: -2.1978

Max Act: 1.9195. Min Act: -0.0000

Data Index: 548255 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 2.1978. Min Range: -2.1978

Max Act: 2.0344. Min Act: -0.0000

Data Index: 518176 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 2.1978. Min Range: -2.1978

Max Act: 1.9590. Min Act: -0.0000

Data Index: 75680 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 2.1978. Min Range: -2.1978

Max Act: 1.8418. Min Act: -0.0000

Data Index: 696420 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 2.1978. Min Range: -2.1978

Max Act: 1.8978. Min Act: -0.0000

Data Index: 978335 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 2.1978. Min Range: -2.1978

Max Act: 1.7652. Min Act: -0.0000

Data Index: 137325 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 2.1978. Min Range: -2.1978

Max Act: 1.7991. Min Act: -0.0000

Data Index: 508696 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 2.1978. Min Range: -2.1978

Max Act: 1.7831. Min Act: -0.0000

Data Index: 205968 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 2.1978. Min Range: -2.1978

Max Act: 1.7209. Min Act: -0.0000

Data Index: 1240003 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 2.1978. Min Range: -2.1978

Max Act: 1.6563. Min Act: -0.0000

Data Index: 1094825 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 2.1978. Min Range: -2.1978

Max Act: 1.6417. Min Act: -0.0000

Data Index: 307210 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 2.1978. Min Range: -2.1978

Max Act: 1.6216. Min Act: -0.0000

Data Index: 876502 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 2.1978. Min Range: -2.1978

Max Act: 1.4854. Min Act: -0.0000

Data Index: 388434 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 2.1978. Min Range: -2.1978

Max Act: 1.4724. Min Act: -0.0000

Data Index: 366149 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 2.1978. Min Range: -2.1978

Max Act: 1.5443. Min Act: -0.0000

Data Index: 533465 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 2.1978. Min Range: -2.1978

Max Act: 1.2894. Min Act: -0.0000

Data Index: 128775 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 2.1978. Min Range: -2.1978

Max Act: 1.4428. Min Act: -0.0000

Data Index: 658944 (C4 (Web Text))

Max Activating Token Index: 37