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

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

Neuron 4858 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: 2.3476. Min Range: -2.3476

Max Act: 2.3476. Min Act: -0.0000

Data Index: 519493 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 2.3476. Min Range: -2.3476

Max Act: 2.1888. Min Act: -0.0000

Data Index: 1178117 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 2.3476. Min Range: -2.3476

Max Act: 1.9504. Min Act: -0.0000

Data Index: 918037 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 2.3476. Min Range: -2.3476

Max Act: 1.9372. Min Act: -0.0000

Data Index: 466343 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 2.3476. Min Range: -2.3476

Max Act: 2.0424. Min Act: -0.0000

Data Index: 1064798 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 2.3476. Min Range: -2.3476

Max Act: 2.0172. Min Act: -0.0000

Data Index: 175767 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 2.3476. Min Range: -2.3476

Max Act: 2.0207. Min Act: -0.0000

Data Index: 375928 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 2.3476. Min Range: -2.3476

Max Act: 1.9927. Min Act: -0.0000

Data Index: 1256922 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 2.3476. Min Range: -2.3476

Max Act: 1.7754. Min Act: -0.0000

Data Index: 1230390 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 2.3476. Min Range: -2.3476

Max Act: 1.7803. Min Act: -0.0000

Data Index: 1230605 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 2.3476. Min Range: -2.3476

Max Act: 1.6450. Min Act: -0.0000

Data Index: 491689 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 2.3476. Min Range: -2.3476

Max Act: 1.7474. Min Act: -0.0000

Data Index: 252015 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 2.3476. Min Range: -2.3476

Max Act: 1.7287. Min Act: -0.0000

Data Index: 555019 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 2.3476. Min Range: -2.3476

Max Act: 1.8319. Min Act: -0.0000

Data Index: 1022673 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 2.3476. Min Range: -2.3476

Max Act: 1.7192. Min Act: -0.0000

Data Index: 837798 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 2.3476. Min Range: -2.3476

Max Act: 1.6181. Min Act: -0.0000

Data Index: 236191 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 2.3476. Min Range: -2.3476

Max Act: 1.6938. Min Act: -0.0000

Data Index: 1116851 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 2.3476. Min Range: -2.3476

Max Act: 1.6057. Min Act: -0.0000

Data Index: 1181799 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 2.3476. Min Range: -2.3476

Max Act: 1.6860. Min Act: -0.0000

Data Index: 273214 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 2.3476. Min Range: -2.3476

Max Act: 1.6743. Min Act: -0.0000

Data Index: 6066 (C4 (Web Text))

Max Activating Token Index: 375