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

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

Neuron 1518 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: 3.5506. Min Range: -3.5506

Max Act: 3.5506. Min Act: -0.1700

Data Index: 291392 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 3.5506. Min Range: -3.5506

Max Act: 3.4292. Min Act: -0.1700

Data Index: 1189427 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 3.5506. Min Range: -3.5506

Max Act: 3.3473. Min Act: -0.1699

Data Index: 1242319 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 3.5506. Min Range: -3.5506

Max Act: 3.3307. Min Act: -0.1700

Data Index: 811722 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 3.5506. Min Range: -3.5506

Max Act: 3.3024. Min Act: -0.1700

Data Index: 443994 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 3.5506. Min Range: -3.5506

Max Act: 3.3052. Min Act: -0.1699

Data Index: 615217 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 3.5506. Min Range: -3.5506

Max Act: 3.3151. Min Act: -0.1700

Data Index: 517464 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 3.5506. Min Range: -3.5506

Max Act: 3.2688. Min Act: -0.1700

Data Index: 721541 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 3.5506. Min Range: -3.5506

Max Act: 3.2798. Min Act: -0.1691

Data Index: 605009 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 3.5506. Min Range: -3.5506

Max Act: 3.2653. Min Act: -0.1700

Data Index: 180724 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 3.5506. Min Range: -3.5506

Max Act: 3.2566. Min Act: -0.1699

Data Index: 596529 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 3.5506. Min Range: -3.5506

Max Act: 3.2664. Min Act: -0.1700

Data Index: 847310 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 3.5506. Min Range: -3.5506

Max Act: 3.2615. Min Act: -0.1700

Data Index: 1078086 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 3.5506. Min Range: -3.5506

Max Act: 3.2363. Min Act: -0.1700

Data Index: 1476150 (Python Code)

Max Activating Token Index: 774

Text #14

Max Range: 3.5506. Min Range: -3.5506

Max Act: 3.1999. Min Act: -0.1700

Data Index: 277769 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 3.5506. Min Range: -3.5506

Max Act: 3.2129. Min Act: -0.1700

Data Index: 347946 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 3.5506. Min Range: -3.5506

Max Act: 3.2234. Min Act: -0.1700

Data Index: 1127452 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 3.5506. Min Range: -3.5506

Max Act: 3.2306. Min Act: -0.1700

Data Index: 728405 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 3.5506. Min Range: -3.5506

Max Act: 3.2123. Min Act: -0.1700

Data Index: 257569 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 3.5506. Min Range: -3.5506

Max Act: 3.2199. Min Act: -0.1700

Data Index: 798771 (C4 (Web Text))

Max Activating Token Index: 479