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

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

Neuron 1624 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: 3.5159. Min Range: -3.5159

Max Act: 3.5159. Min Act: -0.1700

Data Index: 1212996 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.4532. Min Act: -0.1700

Data Index: 487567 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.3375. Min Act: -0.1700

Data Index: 1034650 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.3334. Min Act: -0.1700

Data Index: 1036452 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.2801. Min Act: -0.1700

Data Index: 1342888 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.2819. Min Act: -0.1700

Data Index: 1121369 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.2829. Min Act: -0.1700

Data Index: 224219 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.2619. Min Act: -0.1700

Data Index: 985203 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.2353. Min Act: -0.1700

Data Index: 1335662 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.2421. Min Act: -0.1700

Data Index: 1019816 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.2412. Min Act: -0.1700

Data Index: 363866 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.2486. Min Act: -0.1700

Data Index: 697858 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.2489. Min Act: -0.1700

Data Index: 1309069 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.2341. Min Act: -0.1700

Data Index: 1213765 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.2422. Min Act: -0.1700

Data Index: 144264 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.2384. Min Act: -0.1700

Data Index: 1039305 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.2168. Min Act: -0.1700

Data Index: 590225 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.2105. Min Act: -0.1700

Data Index: 685144 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.2232. Min Act: -0.1700

Data Index: 683505 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.2134. Min Act: -0.1700

Data Index: 619101 (C4 (Web Text))

Max Activating Token Index: 25