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

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

Neuron 209 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: 5.1953. Min Range: -5.1953

Max Act: 5.0703. Min Act: -0.1700

Data Index: 421711 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 5.1953. Min Range: -5.1953

Max Act: 5.1953. Min Act: -0.1700

Data Index: 711823 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 5.1953. Min Range: -5.1953

Max Act: 5.0391. Min Act: -0.1700

Data Index: 624253 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 5.1953. Min Range: -5.1953

Max Act: 5.1016. Min Act: -0.1700

Data Index: 178644 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 5.1953. Min Range: -5.1953

Max Act: 4.9766. Min Act: -0.1700

Data Index: 445895 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 5.1953. Min Range: -5.1953

Max Act: 5.0078. Min Act: -0.1700

Data Index: 561553 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 5.1953. Min Range: -5.1953

Max Act: 4.9453. Min Act: -0.1700

Data Index: 37394 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 5.1953. Min Range: -5.1953

Max Act: 5.0078. Min Act: -0.1700

Data Index: 909509 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 5.1953. Min Range: -5.1953

Max Act: 5.1016. Min Act: -0.1700

Data Index: 388126 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 5.1953. Min Range: -5.1953

Max Act: 5.0703. Min Act: -0.1700

Data Index: 413156 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 5.1953. Min Range: -5.1953

Max Act: 5.0078. Min Act: -0.1700

Data Index: 524167 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 5.1953. Min Range: -5.1953

Max Act: 5.0391. Min Act: -0.1700

Data Index: 1097540 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 5.1953. Min Range: -5.1953

Max Act: 5.0391. Min Act: -0.1700

Data Index: 1213189 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 5.1953. Min Range: -5.1953

Max Act: 5.0703. Min Act: -0.1700

Data Index: 633577 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 5.1953. Min Range: -5.1953

Max Act: 5.0078. Min Act: -0.1700

Data Index: 655818 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 5.1953. Min Range: -5.1953

Max Act: 4.9453. Min Act: -0.1700

Data Index: 502629 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 5.1953. Min Range: -5.1953

Max Act: 5.0703. Min Act: -0.1700

Data Index: 628451 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 5.1953. Min Range: -5.1953

Max Act: 5.0703. Min Act: -0.1700

Data Index: 23676 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 5.1953. Min Range: -5.1953

Max Act: 4.9766. Min Act: -0.1700

Data Index: 678446 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 5.1953. Min Range: -5.1953

Max Act: 4.9141. Min Act: -0.1700

Data Index: 704158 (C4 (Web Text))

Max Activating Token Index: 762