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

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

Neuron 608 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: 3.2575. Min Range: -3.2575

Max Act: 3.2575. Min Act: -0.1700

Data Index: 227533 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 3.2575. Min Range: -3.2575

Max Act: 3.2418. Min Act: -0.1700

Data Index: 86 (C4 (Web Text))

Max Activating Token Index: 478

Text #2

Max Range: 3.2575. Min Range: -3.2575

Max Act: 3.1946. Min Act: -0.1700

Data Index: 287921 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 3.2575. Min Range: -3.2575

Max Act: 3.1946. Min Act: -0.1700

Data Index: 1049262 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 3.2575. Min Range: -3.2575

Max Act: 3.1631. Min Act: -0.1700

Data Index: 1225969 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 3.2575. Min Range: -3.2575

Max Act: 3.1946. Min Act: -0.1700

Data Index: 1034513 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 3.2575. Min Range: -3.2575

Max Act: 3.1631. Min Act: -0.1700

Data Index: 639854 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 3.2575. Min Range: -3.2575

Max Act: 3.1631. Min Act: -0.1700

Data Index: 655848 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 3.2575. Min Range: -3.2575

Max Act: 3.1789. Min Act: -0.1700

Data Index: 380923 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 3.2575. Min Range: -3.2575

Max Act: 3.1474. Min Act: -0.1700

Data Index: 985186 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 3.2575. Min Range: -3.2575

Max Act: 3.1474. Min Act: -0.1700

Data Index: 511950 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 3.2575. Min Range: -3.2575

Max Act: 3.1474. Min Act: -0.1700

Data Index: 727465 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 3.2575. Min Range: -3.2575

Max Act: 3.0844. Min Act: -0.1700

Data Index: 93879 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 3.2575. Min Range: -3.2575

Max Act: 3.0844. Min Act: -0.1700

Data Index: 1060485 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 3.2575. Min Range: -3.2575

Max Act: 3.0844. Min Act: -0.1700

Data Index: 450886 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 3.2575. Min Range: -3.2575

Max Act: 3.0844. Min Act: -0.1700

Data Index: 550247 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 3.2575. Min Range: -3.2575

Max Act: 3.0686. Min Act: -0.1700

Data Index: 1069124 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 3.2575. Min Range: -3.2575

Max Act: 3.0686. Min Act: -0.1700

Data Index: 986913 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 3.2575. Min Range: -3.2575

Max Act: 3.0528. Min Act: -0.1700

Data Index: 786817 (C4 (Web Text))

Max Activating Token Index: 617

Text #19

Max Range: 3.2575. Min Range: -3.2575

Max Act: 3.0844. Min Act: -0.1700

Data Index: 883265 (C4 (Web Text))

Max Activating Token Index: 915