Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 740 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.5224. Min Range: -3.5224

Max Act: 3.4910. Min Act: -0.1700

Data Index: 1167667 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 3.5224. Min Range: -3.5224

Max Act: 3.5224. Min Act: -0.1700

Data Index: 1185791 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 3.5224. Min Range: -3.5224

Max Act: 3.4597. Min Act: -0.1700

Data Index: 192544 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 3.5224. Min Range: -3.5224

Max Act: 3.4597. Min Act: -0.1700

Data Index: 13649 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 3.5224. Min Range: -3.5224

Max Act: 3.3969. Min Act: -0.1700

Data Index: 859636 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 3.5224. Min Range: -3.5224

Max Act: 3.4283. Min Act: -0.1700

Data Index: 586622 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 3.5224. Min Range: -3.5224

Max Act: 3.4283. Min Act: -0.1700

Data Index: 360522 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 3.5224. Min Range: -3.5224

Max Act: 3.3656. Min Act: -0.1700

Data Index: 1307677 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 3.5224. Min Range: -3.5224

Max Act: 3.3969. Min Act: -0.1700

Data Index: 413399 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 3.5224. Min Range: -3.5224

Max Act: 3.3969. Min Act: -0.1700

Data Index: 162823 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 3.5224. Min Range: -3.5224

Max Act: 3.3969. Min Act: -0.1700

Data Index: 424020 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 3.5224. Min Range: -3.5224

Max Act: 3.3969. Min Act: -0.1700

Data Index: 803454 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 3.5224. Min Range: -3.5224

Max Act: 3.3969. Min Act: -0.1700

Data Index: 185846 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 3.5224. Min Range: -3.5224

Max Act: 3.3656. Min Act: -0.1700

Data Index: 455667 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 3.5224. Min Range: -3.5224

Max Act: 3.3969. Min Act: -0.1700

Data Index: 299772 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 3.5224. Min Range: -3.5224

Max Act: 3.3969. Min Act: -0.1700

Data Index: 201049 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 3.5224. Min Range: -3.5224

Max Act: 3.3656. Min Act: -0.1700

Data Index: 34759 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 3.5224. Min Range: -3.5224

Max Act: 3.3342. Min Act: -0.1700

Data Index: 817636 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 3.5224. Min Range: -3.5224

Max Act: 3.3342. Min Act: -0.1700

Data Index: 169341 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 3.5224. Min Range: -3.5224

Max Act: 3.3969. Min Act: -0.1700

Data Index: 511467 (C4 (Web Text))

Max Activating Token Index: 619