Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 386 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8184. Min Range: -3.8184

Max Act: 3.8184. Min Act: -0.1700

Data Index: 206680 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 3.8184. Min Range: -3.8184

Max Act: 3.7715. Min Act: -0.1700

Data Index: 1124481 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 3.8184. Min Range: -3.8184

Max Act: 3.6933. Min Act: -0.1700

Data Index: 319542 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 3.8184. Min Range: -3.8184

Max Act: 3.7246. Min Act: -0.1700

Data Index: 456890 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 3.8184. Min Range: -3.8184

Max Act: 3.6463. Min Act: -0.1700

Data Index: 747700 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 3.8184. Min Range: -3.8184

Max Act: 3.5994. Min Act: -0.1700

Data Index: 247046 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 3.8184. Min Range: -3.8184

Max Act: 3.5994. Min Act: -0.1700

Data Index: 238191 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 3.8184. Min Range: -3.8184

Max Act: 3.5524. Min Act: -0.1700

Data Index: 436879 (C4 (Web Text))

Max Activating Token Index: 776

Text #8

Max Range: 3.8184. Min Range: -3.8184

Max Act: 3.5681. Min Act: -0.1700

Data Index: 1228403 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 3.8184. Min Range: -3.8184

Max Act: 3.5524. Min Act: -0.1700

Data Index: 1033471 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 3.8184. Min Range: -3.8184

Max Act: 3.5054. Min Act: -0.1700

Data Index: 487723 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 3.8184. Min Range: -3.8184

Max Act: 3.5054. Min Act: -0.1700

Data Index: 1120532 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 3.8184. Min Range: -3.8184

Max Act: 3.4897. Min Act: -0.1700

Data Index: 478428 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 3.8184. Min Range: -3.8184

Max Act: 3.4897. Min Act: -0.1700

Data Index: 84710 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 3.8184. Min Range: -3.8184

Max Act: 3.4897. Min Act: -0.1700

Data Index: 497025 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 3.8184. Min Range: -3.8184

Max Act: 3.4584. Min Act: -0.1700

Data Index: 317573 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 3.8184. Min Range: -3.8184

Max Act: 3.4584. Min Act: -0.1700

Data Index: 1001348 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 3.8184. Min Range: -3.8184

Max Act: 3.4270. Min Act: -0.1700

Data Index: 586866 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 3.8184. Min Range: -3.8184

Max Act: 3.4584. Min Act: -0.1700

Data Index: 974105 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 3.8184. Min Range: -3.8184

Max Act: 3.4114. Min Act: -0.1700

Data Index: 209655 (C4 (Web Text))

Max Activating Token Index: 299