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

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

Neuron 1449 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4625. Min Range: -3.4625

Max Act: 3.4625. Min Act: -0.1700

Data Index: 314337 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 3.4625. Min Range: -3.4625

Max Act: 3.3056. Min Act: -0.1700

Data Index: 37381 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 3.4625. Min Range: -3.4625

Max Act: 3.2899. Min Act: -0.1700

Data Index: 979666 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 3.4625. Min Range: -3.4625

Max Act: 3.2585. Min Act: -0.1700

Data Index: 949023 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 3.4625. Min Range: -3.4625

Max Act: 3.2742. Min Act: -0.1700

Data Index: 902828 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 3.4625. Min Range: -3.4625

Max Act: 3.2585. Min Act: -0.1700

Data Index: 1051361 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 3.4625. Min Range: -3.4625

Max Act: 3.2585. Min Act: -0.1700

Data Index: 397614 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 3.4625. Min Range: -3.4625

Max Act: 3.2585. Min Act: -0.1700

Data Index: 95241 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 3.4625. Min Range: -3.4625

Max Act: 3.2899. Min Act: -0.1700

Data Index: 746808 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 3.4625. Min Range: -3.4625

Max Act: 3.2428. Min Act: -0.1700

Data Index: 852919 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 3.4625. Min Range: -3.4625

Max Act: 3.2428. Min Act: -0.1700

Data Index: 899381 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 3.4625. Min Range: -3.4625

Max Act: 3.2271. Min Act: -0.1700

Data Index: 1027606 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 3.4625. Min Range: -3.4625

Max Act: 3.2113. Min Act: -0.1700

Data Index: 362723 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 3.4625. Min Range: -3.4625

Max Act: 3.1956. Min Act: -0.1700

Data Index: 830463 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 3.4625. Min Range: -3.4625

Max Act: 3.1956. Min Act: -0.1700

Data Index: 902145 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 3.4625. Min Range: -3.4625

Max Act: 3.1799. Min Act: -0.1700

Data Index: 358764 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 3.4625. Min Range: -3.4625

Max Act: 3.1799. Min Act: -0.1700

Data Index: 880541 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 3.4625. Min Range: -3.4625

Max Act: 3.1799. Min Act: -0.1700

Data Index: 220251 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 3.4625. Min Range: -3.4625

Max Act: 3.1641. Min Act: -0.1700

Data Index: 287306 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 3.4625. Min Range: -3.4625

Max Act: 3.1641. Min Act: -0.1700

Data Index: 387175 (C4 (Web Text))

Max Activating Token Index: 886