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

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

Neuron 4506 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2639. Min Act: -0.0000

Data Index: 1331672 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2685. Min Act: -0.0000

Data Index: 12833 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2586. Min Act: -0.0000

Data Index: 817596 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2518. Min Act: -0.0000

Data Index: 641987 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2432. Min Act: -0.0000

Data Index: 545284 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2451. Min Act: -0.0000

Data Index: 1189791 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2442. Min Act: -0.0000

Data Index: 916424 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2419. Min Act: -0.0000

Data Index: 1142769 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2339. Min Act: -0.0000

Data Index: 597197 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2302. Min Act: -0.0000

Data Index: 250989 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2284. Min Act: -0.0000

Data Index: 1274251 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2293. Min Act: -0.0000

Data Index: 2006 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2361. Min Act: -0.0000

Data Index: 919327 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2366. Min Act: -0.0000

Data Index: 640261 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2427. Min Act: -0.0000

Data Index: 853909 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2289. Min Act: -0.0000

Data Index: 895148 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2295. Min Act: -0.0000

Data Index: 1043647 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2273. Min Act: -0.0000

Data Index: 1049554 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2359. Min Act: -0.0000

Data Index: 469210 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2284. Min Act: -0.0000

Data Index: 374217 (C4 (Web Text))

Max Activating Token Index: 202