Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1447 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.2338. Min Range: -5.2338

Max Act: 5.2338. Min Act: -0.1700

Data Index: 711097 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 5.2338. Min Range: -5.2338

Max Act: 5.1713. Min Act: -0.1700

Data Index: 853299 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 5.2338. Min Range: -5.2338

Max Act: 5.0150. Min Act: -0.1700

Data Index: 644253 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 5.2338. Min Range: -5.2338

Max Act: 4.9838. Min Act: -0.1700

Data Index: 1002450 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 5.2338. Min Range: -5.2338

Max Act: 4.9525. Min Act: -0.1700

Data Index: 1171487 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 5.2338. Min Range: -5.2338

Max Act: 4.9525. Min Act: -0.1700

Data Index: 831121 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 5.2338. Min Range: -5.2338

Max Act: 4.8900. Min Act: -0.1700

Data Index: 180511 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 5.2338. Min Range: -5.2338

Max Act: 4.8587. Min Act: -0.1700

Data Index: 965942 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 5.2338. Min Range: -5.2338

Max Act: 4.8900. Min Act: -0.1700

Data Index: 296471 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 5.2338. Min Range: -5.2338

Max Act: 4.8587. Min Act: -0.1700

Data Index: 1322410 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 5.2338. Min Range: -5.2338

Max Act: 4.7962. Min Act: -0.1700

Data Index: 255052 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 5.2338. Min Range: -5.2338

Max Act: 4.8275. Min Act: -0.1700

Data Index: 493854 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 5.2338. Min Range: -5.2338

Max Act: 4.7962. Min Act: -0.1700

Data Index: 20866 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 5.2338. Min Range: -5.2338

Max Act: 4.8275. Min Act: -0.1700

Data Index: 1170701 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 5.2338. Min Range: -5.2338

Max Act: 4.8275. Min Act: -0.1700

Data Index: 898221 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 5.2338. Min Range: -5.2338

Max Act: 4.7650. Min Act: -0.1700

Data Index: 983097 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 5.2338. Min Range: -5.2338

Max Act: 4.7962. Min Act: -0.1700

Data Index: 654304 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 5.2338. Min Range: -5.2338

Max Act: 4.7337. Min Act: -0.1700

Data Index: 108060 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 5.2338. Min Range: -5.2338

Max Act: 4.7650. Min Act: -0.1700

Data Index: 294368 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 5.2338. Min Range: -5.2338

Max Act: 4.7650. Min Act: -0.1700

Data Index: 451834 (C4 (Web Text))

Max Activating Token Index: 273