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

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

Neuron 387 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: 4.6827. Min Range: -4.6827

Max Act: 4.6827. Min Act: -0.1700

Data Index: 862957 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 4.6827. Min Range: -4.6827

Max Act: 4.6686. Min Act: -0.1700

Data Index: 750593 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 4.6827. Min Range: -4.6827

Max Act: 4.5969. Min Act: -0.1700

Data Index: 1311135 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 4.6827. Min Range: -4.6827

Max Act: 4.6382. Min Act: -0.1700

Data Index: 956084 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 4.6827. Min Range: -4.6827

Max Act: 4.6493. Min Act: -0.1700

Data Index: 150924 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 4.6827. Min Range: -4.6827

Max Act: 4.6177. Min Act: -0.1700

Data Index: 709440 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 4.6827. Min Range: -4.6827

Max Act: 4.5900. Min Act: -0.1700

Data Index: 243194 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 4.6827. Min Range: -4.6827

Max Act: 4.5754. Min Act: -0.1700

Data Index: 766225 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 4.6827. Min Range: -4.6827

Max Act: 4.6326. Min Act: -0.1700

Data Index: 852712 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 4.6827. Min Range: -4.6827

Max Act: 4.5603. Min Act: -0.1700

Data Index: 164259 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 4.6827. Min Range: -4.6827

Max Act: 4.5990. Min Act: -0.1700

Data Index: 443299 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 4.6827. Min Range: -4.6827

Max Act: 4.5844. Min Act: -0.1700

Data Index: 694317 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 4.6827. Min Range: -4.6827

Max Act: 4.5907. Min Act: -0.1700

Data Index: 127496 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 4.6827. Min Range: -4.6827

Max Act: 4.5888. Min Act: -0.1700

Data Index: 872366 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 4.6827. Min Range: -4.6827

Max Act: 4.5386. Min Act: -0.1700

Data Index: 600550 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 4.6827. Min Range: -4.6827

Max Act: 4.5562. Min Act: -0.1700

Data Index: 71452 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 4.6827. Min Range: -4.6827

Max Act: 4.5595. Min Act: -0.1700

Data Index: 469056 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 4.6827. Min Range: -4.6827

Max Act: 4.5737. Min Act: -0.1700

Data Index: 587732 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 4.6827. Min Range: -4.6827

Max Act: 4.5603. Min Act: -0.1700

Data Index: 723085 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 4.6827. Min Range: -4.6827

Max Act: 4.5289. Min Act: -0.1700

Data Index: 447145 (C4 (Web Text))

Max Activating Token Index: 517