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

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

Neuron 1711 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: 3.1567. Min Range: -3.1567

Max Act: 3.1567. Min Act: -0.1700

Data Index: 131710 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 3.1567. Min Range: -3.1567

Max Act: 3.1567. Min Act: -0.1700

Data Index: 490535 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 3.1567. Min Range: -3.1567

Max Act: 3.1409. Min Act: -0.1700

Data Index: 120659 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 3.1567. Min Range: -3.1567

Max Act: 3.0305. Min Act: -0.1700

Data Index: 714583 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 3.1567. Min Range: -3.1567

Max Act: 2.9989. Min Act: -0.1700

Data Index: 119795 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 3.1567. Min Range: -3.1567

Max Act: 2.9989. Min Act: -0.1700

Data Index: 1199925 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 3.1567. Min Range: -3.1567

Max Act: 2.9989. Min Act: -0.1700

Data Index: 576616 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 3.1567. Min Range: -3.1567

Max Act: 2.9831. Min Act: -0.1700

Data Index: 173090 (C4 (Web Text))

Max Activating Token Index: 666

Text #8

Max Range: 3.1567. Min Range: -3.1567

Max Act: 2.9673. Min Act: -0.1700

Data Index: 1032153 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 3.1567. Min Range: -3.1567

Max Act: 2.9673. Min Act: -0.1700

Data Index: 944622 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 3.1567. Min Range: -3.1567

Max Act: 2.9989. Min Act: -0.1700

Data Index: 81239 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 3.1567. Min Range: -3.1567

Max Act: 2.9831. Min Act: -0.1700

Data Index: 657662 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 3.1567. Min Range: -3.1567

Max Act: 2.9673. Min Act: -0.1700

Data Index: 765439 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 3.1567. Min Range: -3.1567

Max Act: 2.9673. Min Act: -0.1700

Data Index: 1028223 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 3.1567. Min Range: -3.1567

Max Act: 2.9673. Min Act: -0.1700

Data Index: 285964 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 3.1567. Min Range: -3.1567

Max Act: 2.9673. Min Act: -0.1700

Data Index: 439856 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 3.1567. Min Range: -3.1567

Max Act: 2.9514. Min Act: -0.1700

Data Index: 835134 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 3.1567. Min Range: -3.1567

Max Act: 2.9356. Min Act: -0.1700

Data Index: 393833 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 3.1567. Min Range: -3.1567

Max Act: 2.9356. Min Act: -0.1700

Data Index: 396074 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 3.1567. Min Range: -3.1567

Max Act: 2.9356. Min Act: -0.1700

Data Index: 892293 (C4 (Web Text))

Max Activating Token Index: 157