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

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

Neuron 1503 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: 3.4484. Min Range: -3.4484

Max Act: 3.4484. Min Act: -0.1700

Data Index: 913986 (C4 (Web Text))

Max Activating Token Index: 475

Text #1

Max Range: 3.4484. Min Range: -3.4484

Max Act: 3.3526. Min Act: -0.1699

Data Index: 187306 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 3.4484. Min Range: -3.4484

Max Act: 3.2753. Min Act: -0.1700

Data Index: 668222 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 3.4484. Min Range: -3.4484

Max Act: 3.2173. Min Act: -0.1700

Data Index: 430432 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 3.4484. Min Range: -3.4484

Max Act: 3.2069. Min Act: -0.1700

Data Index: 557774 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 3.4484. Min Range: -3.4484

Max Act: 3.2057. Min Act: -0.1700

Data Index: 1051126 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 3.4484. Min Range: -3.4484

Max Act: 3.1889. Min Act: -0.1700

Data Index: 727437 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 3.4484. Min Range: -3.4484

Max Act: 3.1781. Min Act: -0.1700

Data Index: 1257200 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 3.4484. Min Range: -3.4484

Max Act: 3.1803. Min Act: -0.1700

Data Index: 556361 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 3.4484. Min Range: -3.4484

Max Act: 3.1686. Min Act: -0.1700

Data Index: 929201 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 3.4484. Min Range: -3.4484

Max Act: 3.1569. Min Act: -0.1700

Data Index: 513920 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 3.4484. Min Range: -3.4484

Max Act: 3.1255. Min Act: -0.1700

Data Index: 717117 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 3.4484. Min Range: -3.4484

Max Act: 3.1375. Min Act: -0.1700

Data Index: 323797 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 3.4484. Min Range: -3.4484

Max Act: 3.1243. Min Act: -0.1700

Data Index: 327984 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 3.4484. Min Range: -3.4484

Max Act: 3.1283. Min Act: -0.1700

Data Index: 1346700 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 3.4484. Min Range: -3.4484

Max Act: 3.0897. Min Act: -0.1700

Data Index: 227257 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 3.4484. Min Range: -3.4484

Max Act: 3.0958. Min Act: -0.1690

Data Index: 682333 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 3.4484. Min Range: -3.4484

Max Act: 3.0961. Min Act: -0.1700

Data Index: 311116 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 3.4484. Min Range: -3.4484

Max Act: 3.0902. Min Act: -0.1700

Data Index: 428596 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 3.4484. Min Range: -3.4484

Max Act: 3.0996. Min Act: -0.1700

Data Index: 920752 (C4 (Web Text))

Max Activating Token Index: 990