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

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

Neuron 1182 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: 3.5518. Min Range: -3.5518

Max Act: 3.5518. Min Act: -0.1700

Data Index: 39348 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3972. Min Act: -0.1700

Data Index: 892932 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3484. Min Act: -0.1700

Data Index: 33296 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3401. Min Act: -0.1700

Data Index: 1108604 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3309. Min Act: -0.1700

Data Index: 41355 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3165. Min Act: -0.1700

Data Index: 503931 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.2944. Min Act: -0.1700

Data Index: 427780 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.2713. Min Act: -0.1699

Data Index: 1327586 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.2816. Min Act: -0.1700

Data Index: 503596 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.2457. Min Act: -0.1700

Data Index: 786766 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.2513. Min Act: -0.1700

Data Index: 990056 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.2528. Min Act: -0.1700

Data Index: 70369 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.2290. Min Act: -0.1700

Data Index: 1345894 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.2343. Min Act: -0.1700

Data Index: 1427724 (Python Code)

Max Activating Token Index: 331

Text #14

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.2521. Min Act: -0.1700

Data Index: 655614 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.2439. Min Act: -0.1700

Data Index: 674545 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.2442. Min Act: -0.1700

Data Index: 565086 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.2338. Min Act: -0.1700

Data Index: 78644 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.2263. Min Act: -0.1700

Data Index: 284981 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.2313. Min Act: -0.1700

Data Index: 1144894 (C4 (Web Text))

Max Activating Token Index: 781