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

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

Neuron 639 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: 4.4662. Min Range: -4.4662

Max Act: 4.4662. Min Act: -0.1700

Data Index: 879506 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.4173. Min Act: -0.1700

Data Index: 1155731 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.3779. Min Act: -0.1700

Data Index: 1100509 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.3571. Min Act: -0.1700

Data Index: 474552 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.3305. Min Act: -0.1700

Data Index: 276128 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.3198. Min Act: -0.1700

Data Index: 1277504 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.3288. Min Act: -0.1700

Data Index: 502155 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.3428. Min Act: -0.1700

Data Index: 158919 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.3206. Min Act: -0.1700

Data Index: 183601 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.2971. Min Act: -0.1700

Data Index: 43426 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.3188. Min Act: -0.1700

Data Index: 550228 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.2687. Min Act: -0.1700

Data Index: 48472 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.2861. Min Act: -0.1700

Data Index: 1278693 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.3000. Min Act: -0.1700

Data Index: 456701 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.2696. Min Act: -0.1700

Data Index: 353372 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.2824. Min Act: -0.1700

Data Index: 794599 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.2758. Min Act: -0.1700

Data Index: 98947 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.2843. Min Act: -0.1700

Data Index: 252586 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.2677. Min Act: -0.1700

Data Index: 360028 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.2396. Min Act: -0.1700

Data Index: 147670 (C4 (Web Text))

Max Activating Token Index: 784