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

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

Neuron 1371 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: 4.0540. Min Range: -4.0540

Max Act: 4.0367. Min Act: -0.1700

Data Index: 1006383 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 4.0540. Min Range: -4.0540

Max Act: 4.0540. Min Act: -0.1700

Data Index: 946539 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 4.0540. Min Range: -4.0540

Max Act: 3.9837. Min Act: -0.1700

Data Index: 862673 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 4.0540. Min Range: -4.0540

Max Act: 4.0056. Min Act: -0.1700

Data Index: 517430 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 4.0540. Min Range: -4.0540

Max Act: 3.9950. Min Act: -0.1700

Data Index: 13720 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 4.0540. Min Range: -4.0540

Max Act: 3.9524. Min Act: -0.1700

Data Index: 370233 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 4.0540. Min Range: -4.0540

Max Act: 3.9329. Min Act: -0.1700

Data Index: 1412879 (Python Code)

Max Activating Token Index: 984

Text #7

Max Range: 4.0540. Min Range: -4.0540

Max Act: 3.9144. Min Act: -0.1700

Data Index: 429513 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 4.0540. Min Range: -4.0540

Max Act: 3.9286. Min Act: -0.1700

Data Index: 34601 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 4.0540. Min Range: -4.0540

Max Act: 3.9284. Min Act: -0.1700

Data Index: 1154034 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 4.0540. Min Range: -4.0540

Max Act: 3.9361. Min Act: -0.1700

Data Index: 1257186 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 4.0540. Min Range: -4.0540

Max Act: 3.9186. Min Act: -0.1700

Data Index: 444097 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 4.0540. Min Range: -4.0540

Max Act: 3.9084. Min Act: -0.1700

Data Index: 926975 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 4.0540. Min Range: -4.0540

Max Act: 3.9335. Min Act: -0.1700

Data Index: 154870 (C4 (Web Text))

Max Activating Token Index: 293

Text #14

Max Range: 4.0540. Min Range: -4.0540

Max Act: 3.8975. Min Act: -0.1700

Data Index: 815296 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 4.0540. Min Range: -4.0540

Max Act: 3.8730. Min Act: -0.1700

Data Index: 967751 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 4.0540. Min Range: -4.0540

Max Act: 3.8882. Min Act: -0.1700

Data Index: 553236 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 4.0540. Min Range: -4.0540

Max Act: 3.8998. Min Act: -0.1700

Data Index: 159451 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 4.0540. Min Range: -4.0540

Max Act: 3.8993. Min Act: -0.1700

Data Index: 56721 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 4.0540. Min Range: -4.0540

Max Act: 3.8874. Min Act: -0.1700

Data Index: 1334734 (C4 (Web Text))

Max Activating Token Index: 722