Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1042 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.3145. Min Act: -0.1700

Data Index: 584363 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.2359. Min Act: -0.1700

Data Index: 746209 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.2202. Min Act: -0.1700

Data Index: 817160 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.2044. Min Act: -0.1700

Data Index: 1652350 (Python Code)

Max Activating Token Index: 31

Text #4

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.2202. Min Act: -0.1700

Data Index: 571688 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.2202. Min Act: -0.1700

Data Index: 1031080 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.2202. Min Act: -0.1700

Data Index: 178620 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.2202. Min Act: -0.1700

Data Index: 1129667 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.2044. Min Act: -0.1700

Data Index: 1304044 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.2044. Min Act: -0.1700

Data Index: 401179 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.2044. Min Act: -0.1700

Data Index: 1426601 (Python Code)

Max Activating Token Index: 980

Text #11

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.1730. Min Act: -0.1700

Data Index: 1471335 (Python Code)

Max Activating Token Index: 940

Text #12

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.1572. Min Act: -0.1700

Data Index: 1388946 (Python Code)

Max Activating Token Index: 958

Text #13

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.1730. Min Act: -0.1700

Data Index: 1567974 (Python Code)

Max Activating Token Index: 851

Text #14

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.1887. Min Act: -0.1700

Data Index: 541627 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.1730. Min Act: -0.1700

Data Index: 41068 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.1887. Min Act: -0.1700

Data Index: 687138 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.1887. Min Act: -0.1700

Data Index: 395607 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.1887. Min Act: -0.1700

Data Index: 1060212 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.1887. Min Act: -0.1700

Data Index: 1203883 (C4 (Web Text))

Max Activating Token Index: 654