Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 121 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.3338. Min Act: -0.1700

Data Index: 332874 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.3338. Min Act: -0.1700

Data Index: 158445 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.2395. Min Act: -0.1700

Data Index: 319607 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.2552. Min Act: -0.1700

Data Index: 496512 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.2552. Min Act: -0.1700

Data Index: 589021 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.2238. Min Act: -0.1700

Data Index: 1293604 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.2081. Min Act: -0.1700

Data Index: 865301 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.2238. Min Act: -0.1700

Data Index: 1265597 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.2395. Min Act: -0.1700

Data Index: 190910 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.2395. Min Act: -0.1700

Data Index: 113141 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.2395. Min Act: -0.1700

Data Index: 1252196 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.2395. Min Act: -0.1700

Data Index: 836598 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.2395. Min Act: -0.1700

Data Index: 622794 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.2081. Min Act: -0.1700

Data Index: 912616 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.2081. Min Act: -0.1700

Data Index: 290427 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.2081. Min Act: -0.1700

Data Index: 46416 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.2395. Min Act: -0.1700

Data Index: 986319 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.1923. Min Act: -0.1700

Data Index: 32316 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.1766. Min Act: -0.1700

Data Index: 595060 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.1608. Min Act: -0.1700

Data Index: 1409522 (Python Code)

Max Activating Token Index: 602