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

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

Neuron 1015 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: 4.7593. Min Range: -4.7593

Max Act: 4.7593. Min Act: -0.1699

Data Index: 242083 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 4.7593. Min Range: -4.7593

Max Act: 4.7336. Min Act: -0.1700

Data Index: 1421161 (Python Code)

Max Activating Token Index: 101

Text #2

Max Range: 4.7593. Min Range: -4.7593

Max Act: 4.7061. Min Act: -0.1700

Data Index: 1612901 (Python Code)

Max Activating Token Index: 977

Text #3

Max Range: 4.7593. Min Range: -4.7593

Max Act: 4.6282. Min Act: -0.1700

Data Index: 410709 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 4.7593. Min Range: -4.7593

Max Act: 4.5764. Min Act: -0.1700

Data Index: 1437326 (Python Code)

Max Activating Token Index: 7

Text #5

Max Range: 4.7593. Min Range: -4.7593

Max Act: 4.5194. Min Act: -0.1700

Data Index: 1589384 (Python Code)

Max Activating Token Index: 855

Text #6

Max Range: 4.7593. Min Range: -4.7593

Max Act: 4.4809. Min Act: -0.1700

Data Index: 405655 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 4.7593. Min Range: -4.7593

Max Act: 4.4925. Min Act: -0.1700

Data Index: 1252760 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 4.7593. Min Range: -4.7593

Max Act: 4.4674. Min Act: -0.1700

Data Index: 1626873 (Python Code)

Max Activating Token Index: 22

Text #9

Max Range: 4.7593. Min Range: -4.7593

Max Act: 4.4453. Min Act: -0.1700

Data Index: 1411217 (Python Code)

Max Activating Token Index: 91

Text #10

Max Range: 4.7593. Min Range: -4.7593

Max Act: 4.4485. Min Act: -0.1700

Data Index: 1109096 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 4.7593. Min Range: -4.7593

Max Act: 4.4304. Min Act: -0.1700

Data Index: 1598140 (Python Code)

Max Activating Token Index: 748

Text #12

Max Range: 4.7593. Min Range: -4.7593

Max Act: 4.4130. Min Act: -0.1700

Data Index: 1066035 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 4.7593. Min Range: -4.7593

Max Act: 4.3936. Min Act: -0.1700

Data Index: 1600426 (Python Code)

Max Activating Token Index: 205

Text #14

Max Range: 4.7593. Min Range: -4.7593

Max Act: 4.4079. Min Act: -0.1700

Data Index: 16234 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 4.7593. Min Range: -4.7593

Max Act: 4.3799. Min Act: -0.1700

Data Index: 1643191 (Python Code)

Max Activating Token Index: 265

Text #16

Max Range: 4.7593. Min Range: -4.7593

Max Act: 4.3741. Min Act: -0.1700

Data Index: 1004340 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 4.7593. Min Range: -4.7593

Max Act: 4.3849. Min Act: -0.1700

Data Index: 1232813 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 4.7593. Min Range: -4.7593

Max Act: 4.3815. Min Act: -0.1700

Data Index: 648527 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 4.7593. Min Range: -4.7593

Max Act: 4.3528. Min Act: -0.1700

Data Index: 568599 (C4 (Web Text))

Max Activating Token Index: 917