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

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

Neuron 4845 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5994. Min Range: -4.5994

Max Act: 4.5994. Min Act: -0.0000

Data Index: 759290 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 4.5994. Min Range: -4.5994

Max Act: 4.0907. Min Act: -0.0000

Data Index: 464607 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 4.5994. Min Range: -4.5994

Max Act: 4.1527. Min Act: -0.0000

Data Index: 48167 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 4.5994. Min Range: -4.5994

Max Act: 3.8859. Min Act: -0.0000

Data Index: 483108 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 4.5994. Min Range: -4.5994

Max Act: 3.9848. Min Act: -0.0000

Data Index: 775486 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 4.5994. Min Range: -4.5994

Max Act: 3.7674. Min Act: -0.0000

Data Index: 1356162 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 4.5994. Min Range: -4.5994

Max Act: 3.5153. Min Act: -0.0000

Data Index: 931178 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 4.5994. Min Range: -4.5994

Max Act: 3.4251. Min Act: -0.0000

Data Index: 421641 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 4.5994. Min Range: -4.5994

Max Act: 3.2754. Min Act: -0.0000

Data Index: 1257247 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 4.5994. Min Range: -4.5994

Max Act: 3.3148. Min Act: -0.0000

Data Index: 649176 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 4.5994. Min Range: -4.5994

Max Act: 3.2977. Min Act: -0.0000

Data Index: 540202 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 4.5994. Min Range: -4.5994

Max Act: 3.2827. Min Act: -0.0000

Data Index: 1118982 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 4.5994. Min Range: -4.5994

Max Act: 3.2738. Min Act: -0.0000

Data Index: 1187721 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 4.5994. Min Range: -4.5994

Max Act: 3.1107. Min Act: -0.0000

Data Index: 54986 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 4.5994. Min Range: -4.5994

Max Act: 3.1418. Min Act: -0.0000

Data Index: 819151 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 4.5994. Min Range: -4.5994

Max Act: 2.9483. Min Act: -0.0000

Data Index: 217577 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 4.5994. Min Range: -4.5994

Max Act: 3.0560. Min Act: -0.0000

Data Index: 95332 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 4.5994. Min Range: -4.5994

Max Act: 3.0269. Min Act: -0.0000

Data Index: 28106 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 4.5994. Min Range: -4.5994

Max Act: 2.9897. Min Act: -0.0000

Data Index: 939684 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 4.5994. Min Range: -4.5994

Max Act: 2.8203. Min Act: -0.0000

Data Index: 806168 (C4 (Web Text))

Max Activating Token Index: 236