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

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

Neuron 913 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: 3.8163. Min Range: -3.8163

Max Act: 3.8163. Min Act: -0.1700

Data Index: 849235 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 3.8163. Min Range: -3.8163

Max Act: 3.7068. Min Act: -0.1700

Data Index: 414792 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 3.8163. Min Range: -3.8163

Max Act: 3.5973. Min Act: -0.1700

Data Index: 486197 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 3.8163. Min Range: -3.8163

Max Act: 3.5659. Min Act: -0.1700

Data Index: 1256897 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 3.8163. Min Range: -3.8163

Max Act: 3.5346. Min Act: -0.1700

Data Index: 776618 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 3.8163. Min Range: -3.8163

Max Act: 3.5189. Min Act: -0.1700

Data Index: 289753 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 3.8163. Min Range: -3.8163

Max Act: 3.5033. Min Act: -0.1700

Data Index: 260742 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 3.8163. Min Range: -3.8163

Max Act: 3.4563. Min Act: -0.1700

Data Index: 930723 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 3.8163. Min Range: -3.8163

Max Act: 3.5033. Min Act: -0.1700

Data Index: 681233 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 3.8163. Min Range: -3.8163

Max Act: 3.4876. Min Act: -0.1700

Data Index: 1219456 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 3.8163. Min Range: -3.8163

Max Act: 3.4876. Min Act: -0.1700

Data Index: 807798 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 3.8163. Min Range: -3.8163

Max Act: 3.4406. Min Act: -0.1700

Data Index: 293249 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 3.8163. Min Range: -3.8163

Max Act: 3.4563. Min Act: -0.1700

Data Index: 1283786 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 3.8163. Min Range: -3.8163

Max Act: 3.4406. Min Act: -0.1700

Data Index: 924510 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 3.8163. Min Range: -3.8163

Max Act: 3.4563. Min Act: -0.1700

Data Index: 1043710 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 3.8163. Min Range: -3.8163

Max Act: 3.4406. Min Act: -0.1700

Data Index: 457976 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 3.8163. Min Range: -3.8163

Max Act: 3.4719. Min Act: -0.1700

Data Index: 1170085 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 3.8163. Min Range: -3.8163

Max Act: 3.4249. Min Act: -0.1700

Data Index: 779256 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 3.8163. Min Range: -3.8163

Max Act: 3.4406. Min Act: -0.1700

Data Index: 1132378 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 3.8163. Min Range: -3.8163

Max Act: 3.4406. Min Act: -0.1700

Data Index: 1331202 (C4 (Web Text))

Max Activating Token Index: 1023