Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 410 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.5478. Min Range: -3.5478

Max Act: 3.5478. Min Act: -0.1700

Data Index: 214466 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 3.5478. Min Range: -3.5478

Max Act: 3.4000. Min Act: -0.1700

Data Index: 658918 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 3.5478. Min Range: -3.5478

Max Act: 3.3263. Min Act: -0.1700

Data Index: 668782 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 3.5478. Min Range: -3.5478

Max Act: 3.3223. Min Act: -0.1700

Data Index: 1118073 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 3.5478. Min Range: -3.5478

Max Act: 3.3289. Min Act: -0.1700

Data Index: 1353594 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 3.5478. Min Range: -3.5478

Max Act: 3.3123. Min Act: -0.1700

Data Index: 41507 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 3.5478. Min Range: -3.5478

Max Act: 3.3015. Min Act: -0.1700

Data Index: 84498 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 3.5478. Min Range: -3.5478

Max Act: 3.3079. Min Act: -0.1700

Data Index: 973481 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 3.5478. Min Range: -3.5478

Max Act: 3.3159. Min Act: -0.1700

Data Index: 186469 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 3.5478. Min Range: -3.5478

Max Act: 3.2853. Min Act: -0.1700

Data Index: 603518 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 3.5478. Min Range: -3.5478

Max Act: 3.2798. Min Act: -0.1700

Data Index: 484784 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 3.5478. Min Range: -3.5478

Max Act: 3.2942. Min Act: -0.1700

Data Index: 658795 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 3.5478. Min Range: -3.5478

Max Act: 3.2692. Min Act: -0.1700

Data Index: 533243 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 3.5478. Min Range: -3.5478

Max Act: 3.2377. Min Act: -0.1700

Data Index: 71741 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 3.5478. Min Range: -3.5478

Max Act: 3.2384. Min Act: -0.1700

Data Index: 951683 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 3.5478. Min Range: -3.5478

Max Act: 3.2426. Min Act: -0.1700

Data Index: 689668 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 3.5478. Min Range: -3.5478

Max Act: 3.2369. Min Act: -0.1700

Data Index: 324652 (C4 (Web Text))

Max Activating Token Index: 954

Text #17

Max Range: 3.5478. Min Range: -3.5478

Max Act: 3.2157. Min Act: -0.1700

Data Index: 670710 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 3.5478. Min Range: -3.5478

Max Act: 3.2170. Min Act: -0.1700

Data Index: 46697 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 3.5478. Min Range: -3.5478

Max Act: 3.2364. Min Act: -0.1700

Data Index: 332801 (C4 (Web Text))

Max Activating Token Index: 957