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

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

Neuron 3278 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4390. Min Range: -2.4390

Max Act: 2.4093. Min Act: -0.0000

Data Index: 1001030 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 2.4390. Min Range: -2.4390

Max Act: 2.4390. Min Act: -0.0000

Data Index: 931082 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 2.4390. Min Range: -2.4390

Max Act: 2.2359. Min Act: -0.0000

Data Index: 751214 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 2.4390. Min Range: -2.4390

Max Act: 2.1948. Min Act: -0.0000

Data Index: 370710 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 2.4390. Min Range: -2.4390

Max Act: 2.2673. Min Act: -0.0000

Data Index: 273866 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 2.4390. Min Range: -2.4390

Max Act: 2.2439. Min Act: -0.0000

Data Index: 550023 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 2.4390. Min Range: -2.4390

Max Act: 1.9212. Min Act: -0.0000

Data Index: 1058609 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 2.4390. Min Range: -2.4390

Max Act: 1.9880. Min Act: -0.0000

Data Index: 26294 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 2.4390. Min Range: -2.4390

Max Act: 1.9121. Min Act: -0.0000

Data Index: 956148 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 2.4390. Min Range: -2.4390

Max Act: 1.8201. Min Act: -0.0000

Data Index: 544385 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 2.4390. Min Range: -2.4390

Max Act: 1.9346. Min Act: -0.0000

Data Index: 762626 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 2.4390. Min Range: -2.4390

Max Act: 1.8099. Min Act: -0.0000

Data Index: 126009 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 2.4390. Min Range: -2.4390

Max Act: 1.6522. Min Act: -0.0000

Data Index: 841158 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 2.4390. Min Range: -2.4390

Max Act: 1.7266. Min Act: -0.0000

Data Index: 1224658 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 2.4390. Min Range: -2.4390

Max Act: 1.8000. Min Act: -0.0000

Data Index: 905243 (C4 (Web Text))

Max Activating Token Index: 387

Text #15

Max Range: 2.4390. Min Range: -2.4390

Max Act: 1.6821. Min Act: -0.0000

Data Index: 87639 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 2.4390. Min Range: -2.4390

Max Act: 1.6544. Min Act: -0.0000

Data Index: 696278 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 2.4390. Min Range: -2.4390

Max Act: 1.7456. Min Act: -0.0000

Data Index: 855873 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 2.4390. Min Range: -2.4390

Max Act: 1.7475. Min Act: -0.0000

Data Index: 1128718 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 2.4390. Min Range: -2.4390

Max Act: 1.5236. Min Act: -0.0000

Data Index: 944641 (C4 (Web Text))

Max Activating Token Index: 1016