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

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

Neuron 275 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: 4.6709. Min Range: -4.6709

Max Act: 4.6709. Min Act: -0.1700

Data Index: 884910 (C4 (Web Text))

Max Activating Token Index: 895

Text #1

Max Range: 4.6709. Min Range: -4.6709

Max Act: 4.6607. Min Act: -0.1700

Data Index: 1635246 (Python Code)

Max Activating Token Index: 845

Text #2

Max Range: 4.6709. Min Range: -4.6709

Max Act: 4.6083. Min Act: -0.1700

Data Index: 1180178 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 4.6709. Min Range: -4.6709

Max Act: 4.5932. Min Act: -0.1700

Data Index: 434603 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 4.6709. Min Range: -4.6709

Max Act: 4.5978. Min Act: -0.1700

Data Index: 810393 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 4.6709. Min Range: -4.6709

Max Act: 4.5791. Min Act: -0.1700

Data Index: 1026059 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 4.6709. Min Range: -4.6709

Max Act: 4.5547. Min Act: -0.1700

Data Index: 1228361 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 4.6709. Min Range: -4.6709

Max Act: 4.5411. Min Act: -0.1700

Data Index: 1222489 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 4.6709. Min Range: -4.6709

Max Act: 4.5382. Min Act: -0.1700

Data Index: 952920 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 4.6709. Min Range: -4.6709

Max Act: 4.5423. Min Act: -0.1700

Data Index: 735353 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 4.6709. Min Range: -4.6709

Max Act: 4.5290. Min Act: -0.1700

Data Index: 912391 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 4.6709. Min Range: -4.6709

Max Act: 4.5276. Min Act: -0.1700

Data Index: 1493370 (Python Code)

Max Activating Token Index: 340

Text #12

Max Range: 4.6709. Min Range: -4.6709

Max Act: 4.5294. Min Act: -0.1700

Data Index: 969582 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 4.6709. Min Range: -4.6709

Max Act: 4.5352. Min Act: -0.1700

Data Index: 7034 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 4.6709. Min Range: -4.6709

Max Act: 4.5101. Min Act: -0.1700

Data Index: 1261378 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 4.6709. Min Range: -4.6709

Max Act: 4.5009. Min Act: -0.1700

Data Index: 188765 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 4.6709. Min Range: -4.6709

Max Act: 4.5037. Min Act: -0.1700

Data Index: 1310490 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 4.6709. Min Range: -4.6709

Max Act: 4.5013. Min Act: -0.1700

Data Index: 522846 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 4.6709. Min Range: -4.6709

Max Act: 4.4941. Min Act: -0.1700

Data Index: 388984 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 4.6709. Min Range: -4.6709

Max Act: 4.4833. Min Act: -0.1700

Data Index: 1061390 (C4 (Web Text))

Max Activating Token Index: 326