Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 71 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.5518. Min Range: -5.5518

Max Act: 5.5518. Min Act: -0.1700

Data Index: 532011 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 5.5518. Min Range: -5.5518

Max Act: 5.1455. Min Act: -0.1700

Data Index: 633053 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 5.5518. Min Range: -5.5518

Max Act: 5.0205. Min Act: -0.1700

Data Index: 1252043 (C4 (Web Text))

Max Activating Token Index: 726

Text #3

Max Range: 5.5518. Min Range: -5.5518

Max Act: 5.0205. Min Act: -0.1700

Data Index: 1115830 (C4 (Web Text))

Max Activating Token Index: 610

Text #4

Max Range: 5.5518. Min Range: -5.5518

Max Act: 4.9580. Min Act: -0.1699

Data Index: 884630 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 5.5518. Min Range: -5.5518

Max Act: 4.8643. Min Act: -0.1700

Data Index: 588532 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 5.5518. Min Range: -5.5518

Max Act: 4.8018. Min Act: -0.1700

Data Index: 1075632 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 5.5518. Min Range: -5.5518

Max Act: 4.8330. Min Act: -0.1700

Data Index: 182296 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 5.5518. Min Range: -5.5518

Max Act: 4.7393. Min Act: -0.1700

Data Index: 104343 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 5.5518. Min Range: -5.5518

Max Act: 4.7705. Min Act: -0.1699

Data Index: 736845 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 5.5518. Min Range: -5.5518

Max Act: 4.7393. Min Act: -0.1700

Data Index: 86294 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 5.5518. Min Range: -5.5518

Max Act: 4.7393. Min Act: -0.1699

Data Index: 101104 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 5.5518. Min Range: -5.5518

Max Act: 4.7393. Min Act: -0.1700

Data Index: 931157 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 5.5518. Min Range: -5.5518

Max Act: 4.7393. Min Act: -0.1700

Data Index: 1225643 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 5.5518. Min Range: -5.5518

Max Act: 4.8018. Min Act: -0.1700

Data Index: 1045398 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 5.5518. Min Range: -5.5518

Max Act: 4.7393. Min Act: -0.1700

Data Index: 895311 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 5.5518. Min Range: -5.5518

Max Act: 4.7393. Min Act: -0.1700

Data Index: 580194 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 5.5518. Min Range: -5.5518

Max Act: 4.7080. Min Act: -0.1700

Data Index: 24933 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 5.5518. Min Range: -5.5518

Max Act: 4.7080. Min Act: -0.1700

Data Index: 460053 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 5.5518. Min Range: -5.5518

Max Act: 4.6768. Min Act: -0.1699

Data Index: 98113 (C4 (Web Text))

Max Activating Token Index: 397