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

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

Neuron 1999 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: 3.7223. Min Range: -3.7223

Max Act: 3.7223. Min Act: -0.1700

Data Index: 857648 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.6380. Min Act: -0.1700

Data Index: 67232 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.6190. Min Act: -0.1700

Data Index: 13287 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.6027. Min Act: -0.1700

Data Index: 155088 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.5752. Min Act: -0.1700

Data Index: 245654 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.5610. Min Act: -0.1700

Data Index: 61368 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.5575. Min Act: -0.1700

Data Index: 725998 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.5568. Min Act: -0.1700

Data Index: 1238187 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.5196. Min Act: -0.1700

Data Index: 525609 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.5363. Min Act: -0.1700

Data Index: 937473 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.5022. Min Act: -0.1700

Data Index: 1129032 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.5104. Min Act: -0.1700

Data Index: 1203707 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.4986. Min Act: -0.1700

Data Index: 233567 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.4926. Min Act: -0.1700

Data Index: 1347916 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.4739. Min Act: -0.1700

Data Index: 618395 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.4794. Min Act: -0.1700

Data Index: 355710 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.4607. Min Act: -0.1700

Data Index: 678063 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.4531. Min Act: -0.1700

Data Index: 692015 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.4566. Min Act: -0.1700

Data Index: 437618 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.4585. Min Act: -0.1700

Data Index: 177556 (C4 (Web Text))

Max Activating Token Index: 867