Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 150 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.7299. Min Act: -0.1700

Data Index: 1044663 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.6361. Min Act: -0.1700

Data Index: 1274574 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.5736. Min Act: -0.1700

Data Index: 1202735 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.6361. Min Act: -0.1700

Data Index: 770966 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.6049. Min Act: -0.1700

Data Index: 1594 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.5424. Min Act: -0.1700

Data Index: 867897 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.3861. Min Act: -0.1700

Data Index: 819051 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.3236. Min Act: -0.1700

Data Index: 828883 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.4486. Min Act: -0.1700

Data Index: 583004 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.4174. Min Act: -0.1700

Data Index: 1295122 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.3861. Min Act: -0.1700

Data Index: 761160 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.3549. Min Act: -0.1700

Data Index: 734206 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.3861. Min Act: -0.1700

Data Index: 1020458 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.3549. Min Act: -0.1700

Data Index: 16505 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.3236. Min Act: -0.1700

Data Index: 976027 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.3236. Min Act: -0.1700

Data Index: 531503 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.3861. Min Act: -0.1700

Data Index: 1149823 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.2924. Min Act: -0.1700

Data Index: 330823 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.2924. Min Act: -0.1700

Data Index: 543670 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.2924. Min Act: -0.1700

Data Index: 40383 (C4 (Web Text))

Max Activating Token Index: 775