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

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

Neuron 1834 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: 4.1151. Min Range: -4.1151

Max Act: 4.1151. Min Act: -0.1700

Data Index: 994897 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 4.1151. Min Range: -4.1151

Max Act: 4.0205. Min Act: -0.1700

Data Index: 496066 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 4.1151. Min Range: -4.1151

Max Act: 3.9431. Min Act: -0.1700

Data Index: 622014 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 4.1151. Min Range: -4.1151

Max Act: 3.9464. Min Act: -0.1700

Data Index: 933684 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 4.1151. Min Range: -4.1151

Max Act: 3.9434. Min Act: -0.1700

Data Index: 388207 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 4.1151. Min Range: -4.1151

Max Act: 3.9236. Min Act: -0.1700

Data Index: 709534 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 4.1151. Min Range: -4.1151

Max Act: 3.8848. Min Act: -0.1700

Data Index: 1167223 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 4.1151. Min Range: -4.1151

Max Act: 3.8853. Min Act: -0.1700

Data Index: 1063058 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 4.1151. Min Range: -4.1151

Max Act: 3.8428. Min Act: -0.1700

Data Index: 1337788 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 4.1151. Min Range: -4.1151

Max Act: 3.8482. Min Act: -0.1700

Data Index: 715502 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 4.1151. Min Range: -4.1151

Max Act: 3.8524. Min Act: -0.1700

Data Index: 711117 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 4.1151. Min Range: -4.1151

Max Act: 3.8705. Min Act: -0.1700

Data Index: 895524 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 4.1151. Min Range: -4.1151

Max Act: 3.8649. Min Act: -0.1700

Data Index: 352080 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 4.1151. Min Range: -4.1151

Max Act: 3.8570. Min Act: -0.1700

Data Index: 111313 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 4.1151. Min Range: -4.1151

Max Act: 3.8357. Min Act: -0.1700

Data Index: 1029499 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 4.1151. Min Range: -4.1151

Max Act: 3.8441. Min Act: -0.1700

Data Index: 1242169 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 4.1151. Min Range: -4.1151

Max Act: 3.8302. Min Act: -0.1700

Data Index: 270401 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 4.1151. Min Range: -4.1151

Max Act: 3.8318. Min Act: -0.1700

Data Index: 392024 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 4.1151. Min Range: -4.1151

Max Act: 3.8355. Min Act: -0.1700

Data Index: 764802 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 4.1151. Min Range: -4.1151

Max Act: 3.8297. Min Act: -0.1700

Data Index: 485936 (C4 (Web Text))

Max Activating Token Index: 879