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

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

Neuron 988 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: 3.8425. Min Range: -3.8425

Max Act: 3.8425. Min Act: -0.1700

Data Index: 318418 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.8029. Min Act: -0.1700

Data Index: 129229 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.7201. Min Act: -0.1700

Data Index: 1264951 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.7008. Min Act: -0.1700

Data Index: 1074990 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.6749. Min Act: -0.1700

Data Index: 954087 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.6464. Min Act: -0.1700

Data Index: 1208853 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.6251. Min Act: -0.1700

Data Index: 362618 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.6243. Min Act: -0.1700

Data Index: 1650164 (Python Code)

Max Activating Token Index: 934

Text #8

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.6325. Min Act: -0.1700

Data Index: 81197 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.5896. Min Act: -0.1700

Data Index: 1450926 (Python Code)

Max Activating Token Index: 589

Text #10

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.5641. Min Act: -0.1700

Data Index: 1554575 (Python Code)

Max Activating Token Index: 570

Text #11

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.5534. Min Act: -0.1700

Data Index: 557890 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.5417. Min Act: -0.1700

Data Index: 1234439 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.5330. Min Act: -0.1700

Data Index: 18034 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.5224. Min Act: -0.1700

Data Index: 1147286 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.4986. Min Act: -0.1700

Data Index: 1636861 (Python Code)

Max Activating Token Index: 91

Text #16

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.5076. Min Act: -0.1700

Data Index: 775303 (C4 (Web Text))

Max Activating Token Index: 450

Text #17

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.4921. Min Act: -0.1700

Data Index: 178121 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.4891. Min Act: -0.1700

Data Index: 287268 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.4758. Min Act: -0.1700

Data Index: 340755 (C4 (Web Text))

Max Activating Token Index: 365