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

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

Neuron 53 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7246. Min Range: -5.7246

Max Act: 5.7246. Min Act: -0.1700

Data Index: 6637 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 5.7246. Min Range: -5.7246

Max Act: 5.6309. Min Act: -0.1700

Data Index: 362356 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 5.7246. Min Range: -5.7246

Max Act: 5.4746. Min Act: -0.1700

Data Index: 674262 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 5.7246. Min Range: -5.7246

Max Act: 5.4434. Min Act: -0.1700

Data Index: 773308 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 5.7246. Min Range: -5.7246

Max Act: 5.4434. Min Act: -0.1700

Data Index: 442748 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 5.7246. Min Range: -5.7246

Max Act: 5.3809. Min Act: -0.1700

Data Index: 802765 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 5.7246. Min Range: -5.7246

Max Act: 5.3809. Min Act: -0.1700

Data Index: 898306 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 5.7246. Min Range: -5.7246

Max Act: 5.3809. Min Act: -0.1700

Data Index: 1187958 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 5.7246. Min Range: -5.7246

Max Act: 5.3809. Min Act: -0.1700

Data Index: 1094073 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 5.7246. Min Range: -5.7246

Max Act: 5.3496. Min Act: -0.1700

Data Index: 532224 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 5.7246. Min Range: -5.7246

Max Act: 5.3496. Min Act: -0.1700

Data Index: 1102528 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 5.7246. Min Range: -5.7246

Max Act: 5.3184. Min Act: -0.1700

Data Index: 920318 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 5.7246. Min Range: -5.7246

Max Act: 5.3184. Min Act: -0.1700

Data Index: 51989 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 5.7246. Min Range: -5.7246

Max Act: 5.2559. Min Act: -0.1700

Data Index: 987990 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 5.7246. Min Range: -5.7246

Max Act: 5.2246. Min Act: -0.1700

Data Index: 269051 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 5.7246. Min Range: -5.7246

Max Act: 5.3184. Min Act: -0.1700

Data Index: 1307675 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 5.7246. Min Range: -5.7246

Max Act: 5.2246. Min Act: -0.1699

Data Index: 511595 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 5.7246. Min Range: -5.7246

Max Act: 5.2246. Min Act: -0.1700

Data Index: 276960 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 5.7246. Min Range: -5.7246

Max Act: 5.2559. Min Act: -0.1700

Data Index: 1355184 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 5.7246. Min Range: -5.7246

Max Act: 5.2559. Min Act: -0.1700

Data Index: 1274525 (C4 (Web Text))

Max Activating Token Index: 283