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

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

Neuron 640 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: 3.3175. Min Range: -3.3175

Max Act: 3.3175. Min Act: -0.1700

Data Index: 810957 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.2860. Min Act: -0.1700

Data Index: 1001449 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.2703. Min Act: -0.1700

Data Index: 62314 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.2232. Min Act: -0.1700

Data Index: 528922 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.2232. Min Act: -0.1700

Data Index: 536096 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.1445. Min Act: -0.1700

Data Index: 359572 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.1760. Min Act: -0.1700

Data Index: 1187116 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.1760. Min Act: -0.1700

Data Index: 1092632 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.1445. Min Act: -0.1700

Data Index: 371090 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.1445. Min Act: -0.1700

Data Index: 1048401 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.1287. Min Act: -0.1700

Data Index: 302519 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.1287. Min Act: -0.1700

Data Index: 101674 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.0657. Min Act: -0.1700

Data Index: 939318 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.1130. Min Act: -0.1700

Data Index: 593291 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.1130. Min Act: -0.1700

Data Index: 176386 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.0814. Min Act: -0.1700

Data Index: 721950 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.0972. Min Act: -0.1700

Data Index: 1053681 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.0814. Min Act: -0.1700

Data Index: 1126043 (C4 (Web Text))

Max Activating Token Index: 898

Text #18

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.0814. Min Act: -0.1700

Data Index: 366215 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.0499. Min Act: -0.1700

Data Index: 1056108 (C4 (Web Text))

Max Activating Token Index: 794