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

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

Neuron 1939 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: 4.0958. Min Range: -4.0958

Max Act: 4.0958. Min Act: -0.1699

Data Index: 184514 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 4.0958. Min Range: -4.0958

Max Act: 3.9365. Min Act: -0.1696

Data Index: 246251 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 4.0958. Min Range: -4.0958

Max Act: 3.9146. Min Act: -0.1699

Data Index: 772834 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 4.0958. Min Range: -4.0958

Max Act: 3.9468. Min Act: -0.1700

Data Index: 643373 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 4.0958. Min Range: -4.0958

Max Act: 3.8972. Min Act: -0.1700

Data Index: 511463 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 4.0958. Min Range: -4.0958

Max Act: 3.8440. Min Act: -0.1700

Data Index: 1248423 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 4.0958. Min Range: -4.0958

Max Act: 3.8348. Min Act: -0.1700

Data Index: 1195221 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 4.0958. Min Range: -4.0958

Max Act: 3.8411. Min Act: -0.1700

Data Index: 1116553 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 4.0958. Min Range: -4.0958

Max Act: 3.7784. Min Act: -0.1700

Data Index: 1445596 (Python Code)

Max Activating Token Index: 913

Text #9

Max Range: 4.0958. Min Range: -4.0958

Max Act: 3.8016. Min Act: -0.1700

Data Index: 1107749 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 4.0958. Min Range: -4.0958

Max Act: 3.7859. Min Act: -0.1700

Data Index: 1193593 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 4.0958. Min Range: -4.0958

Max Act: 3.7612. Min Act: -0.1700

Data Index: 471149 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 4.0958. Min Range: -4.0958

Max Act: 3.7557. Min Act: -0.1699

Data Index: 729696 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 4.0958. Min Range: -4.0958

Max Act: 3.7621. Min Act: -0.1699

Data Index: 684879 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 4.0958. Min Range: -4.0958

Max Act: 3.7614. Min Act: -0.1700

Data Index: 916751 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 4.0958. Min Range: -4.0958

Max Act: 3.7614. Min Act: -0.1700

Data Index: 1368804 (Python Code)

Max Activating Token Index: 379

Text #16

Max Range: 4.0958. Min Range: -4.0958

Max Act: 3.7233. Min Act: -0.1698

Data Index: 91884 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 4.0958. Min Range: -4.0958

Max Act: 3.7161. Min Act: -0.1700

Data Index: 1095890 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 4.0958. Min Range: -4.0958

Max Act: 3.7392. Min Act: -0.1700

Data Index: 1220989 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 4.0958. Min Range: -4.0958

Max Act: 3.7220. Min Act: -0.1700

Data Index: 971503 (C4 (Web Text))

Max Activating Token Index: 394