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

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

Neuron 1391 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8895. Min Range: -3.8895

Max Act: 3.8895. Min Act: -0.1699

Data Index: 987492 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 3.8895. Min Range: -3.8895

Max Act: 3.8582. Min Act: -0.1700

Data Index: 269743 (C4 (Web Text))

Max Activating Token Index: 477

Text #2

Max Range: 3.8895. Min Range: -3.8895

Max Act: 3.8113. Min Act: -0.1700

Data Index: 453726 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 3.8895. Min Range: -3.8895

Max Act: 3.8269. Min Act: -0.1699

Data Index: 1028964 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 3.8895. Min Range: -3.8895

Max Act: 3.7956. Min Act: -0.1700

Data Index: 358241 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 3.8895. Min Range: -3.8895

Max Act: 3.7644. Min Act: -0.1699

Data Index: 566994 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 3.8895. Min Range: -3.8895

Max Act: 3.7800. Min Act: -0.1700

Data Index: 395508 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 3.8895. Min Range: -3.8895

Max Act: 3.7644. Min Act: -0.1700

Data Index: 797477 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 3.8895. Min Range: -3.8895

Max Act: 3.7487. Min Act: -0.1700

Data Index: 506800 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 3.8895. Min Range: -3.8895

Max Act: 3.7174. Min Act: -0.1700

Data Index: 1352548 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 3.8895. Min Range: -3.8895

Max Act: 3.7331. Min Act: -0.1700

Data Index: 749935 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 3.8895. Min Range: -3.8895

Max Act: 3.7018. Min Act: -0.1700

Data Index: 1152946 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 3.8895. Min Range: -3.8895

Max Act: 3.7331. Min Act: -0.1700

Data Index: 579092 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 3.8895. Min Range: -3.8895

Max Act: 3.7018. Min Act: -0.1700

Data Index: 916227 (C4 (Web Text))

Max Activating Token Index: 472

Text #14

Max Range: 3.8895. Min Range: -3.8895

Max Act: 3.6861. Min Act: -0.1700

Data Index: 198112 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 3.8895. Min Range: -3.8895

Max Act: 3.6861. Min Act: -0.1700

Data Index: 1259975 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 3.8895. Min Range: -3.8895

Max Act: 3.7018. Min Act: -0.1700

Data Index: 1069160 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 3.8895. Min Range: -3.8895

Max Act: 3.6705. Min Act: -0.1700

Data Index: 248455 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 3.8895. Min Range: -3.8895

Max Act: 3.6705. Min Act: -0.1699

Data Index: 1306940 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 3.8895. Min Range: -3.8895

Max Act: 3.6861. Min Act: -0.1700

Data Index: 933335 (C4 (Web Text))

Max Activating Token Index: 974