Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2228 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.4335. Min Act: -0.0000

Data Index: 1016178 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.4270. Min Act: -0.0000

Data Index: 319681 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.4279. Min Act: -0.0000

Data Index: 4957 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.4261. Min Act: -0.0000

Data Index: 591772 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.4365. Min Act: -0.0000

Data Index: 395745 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.4073. Min Act: -0.0000

Data Index: 492498 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.4296. Min Act: -0.0000

Data Index: 212668 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.4156. Min Act: -0.0000

Data Index: 763393 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3963. Min Act: 0.0000

Data Index: 467759 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3898. Min Act: 0.0000

Data Index: 952048 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3790. Min Act: -0.0000

Data Index: 1164449 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.4122. Min Act: 0.0000

Data Index: 52602 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3792. Min Act: -0.0000

Data Index: 449598 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3861. Min Act: -0.0000

Data Index: 70578 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3670. Min Act: -0.0000

Data Index: 823132 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3857. Min Act: 0.0001

Data Index: 1222440 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3487. Min Act: -0.0000

Data Index: 838766 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3668. Min Act: -0.0000

Data Index: 1227033 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3641. Min Act: -0.0000

Data Index: 1132245 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3502. Min Act: 0.0002

Data Index: 555353 (C4 (Web Text))

Max Activating Token Index: 283