Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3930 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3293. Min Range: -1.3293

Max Act: 1.1995. Min Act: -0.0001

Data Index: 293546 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 1.3293. Min Range: -1.3293

Max Act: 1.1015. Min Act: -0.0001

Data Index: 85002 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 1.3293. Min Range: -1.3293

Max Act: 1.1844. Min Act: -0.0002

Data Index: 1151034 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 1.3293. Min Range: -1.3293

Max Act: 1.3293. Min Act: -0.0001

Data Index: 1298314 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 1.3293. Min Range: -1.3293

Max Act: 1.0691. Min Act: -0.0001

Data Index: 8638 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 1.3293. Min Range: -1.3293

Max Act: 0.9956. Min Act: -0.0001

Data Index: 292946 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 1.3293. Min Range: -1.3293

Max Act: 0.9212. Min Act: -0.0001

Data Index: 1319157 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 1.3293. Min Range: -1.3293

Max Act: 1.0453. Min Act: -0.0001

Data Index: 1193232 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 1.3293. Min Range: -1.3293

Max Act: 0.8678. Min Act: -0.0002

Data Index: 938438 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 1.3293. Min Range: -1.3293

Max Act: 0.8906. Min Act: -0.0002

Data Index: 199064 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 1.3293. Min Range: -1.3293

Max Act: 0.9507. Min Act: -0.0001

Data Index: 810263 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 1.3293. Min Range: -1.3293

Max Act: 0.9242. Min Act: -0.0001

Data Index: 883007 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 1.3293. Min Range: -1.3293

Max Act: 0.9210. Min Act: -0.0001

Data Index: 660543 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 1.3293. Min Range: -1.3293

Max Act: 0.8787. Min Act: -0.0001

Data Index: 141453 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 1.3293. Min Range: -1.3293

Max Act: 0.8667. Min Act: -0.0001

Data Index: 104470 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 1.3293. Min Range: -1.3293

Max Act: 0.8837. Min Act: -0.0002

Data Index: 894347 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 1.3293. Min Range: -1.3293

Max Act: 0.8398. Min Act: -0.0001

Data Index: 257143 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 1.3293. Min Range: -1.3293

Max Act: 0.8811. Min Act: -0.0001

Data Index: 591864 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 1.3293. Min Range: -1.3293

Max Act: 0.8218. Min Act: -0.0001

Data Index: 490951 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 1.3293. Min Range: -1.3293

Max Act: 0.8459. Min Act: -0.0001

Data Index: 1345474 (C4 (Web Text))

Max Activating Token Index: 867