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

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

Neuron 457 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: 3.6256. Min Range: -3.6256

Max Act: 3.6256. Min Act: -0.1700

Data Index: 819943 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 3.6256. Min Range: -3.6256

Max Act: 3.5662. Min Act: -0.1700

Data Index: 1137512 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 3.6256. Min Range: -3.6256

Max Act: 3.5017. Min Act: -0.1700

Data Index: 1003073 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 3.6256. Min Range: -3.6256

Max Act: 3.4867. Min Act: -0.1700

Data Index: 1336845 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 3.6256. Min Range: -3.6256

Max Act: 3.4307. Min Act: -0.1700

Data Index: 1172084 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 3.6256. Min Range: -3.6256

Max Act: 3.3741. Min Act: -0.1700

Data Index: 137928 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 3.6256. Min Range: -3.6256

Max Act: 3.3886. Min Act: -0.1700

Data Index: 41417 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 3.6256. Min Range: -3.6256

Max Act: 3.3227. Min Act: -0.1700

Data Index: 1342029 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 3.6256. Min Range: -3.6256

Max Act: 3.2990. Min Act: -0.1700

Data Index: 1245706 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 3.6256. Min Range: -3.6256

Max Act: 3.2699. Min Act: -0.1700

Data Index: 362737 (C4 (Web Text))

Max Activating Token Index: 751

Text #10

Max Range: 3.6256. Min Range: -3.6256

Max Act: 3.2396. Min Act: -0.1700

Data Index: 915079 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 3.6256. Min Range: -3.6256

Max Act: 3.2442. Min Act: -0.1700

Data Index: 907199 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 3.6256. Min Range: -3.6256

Max Act: 3.2192. Min Act: -0.1700

Data Index: 23062 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 3.6256. Min Range: -3.6256

Max Act: 3.2574. Min Act: -0.1700

Data Index: 573208 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 3.6256. Min Range: -3.6256

Max Act: 3.2387. Min Act: -0.1700

Data Index: 1141640 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 3.6256. Min Range: -3.6256

Max Act: 3.2295. Min Act: -0.1700

Data Index: 887054 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 3.6256. Min Range: -3.6256

Max Act: 3.2273. Min Act: -0.1700

Data Index: 301561 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 3.6256. Min Range: -3.6256

Max Act: 3.2260. Min Act: -0.1700

Data Index: 758870 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 3.6256. Min Range: -3.6256

Max Act: 3.2196. Min Act: -0.1700

Data Index: 312711 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 3.6256. Min Range: -3.6256

Max Act: 3.2346. Min Act: -0.1700

Data Index: 1211764 (C4 (Web Text))

Max Activating Token Index: 778