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

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

Neuron 884 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2669. Min Range: -5.2669

Max Act: 5.2357. Min Act: -0.1700

Data Index: 1213018 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 5.2669. Min Range: -5.2669

Max Act: 5.2669. Min Act: -0.1700

Data Index: 115486 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 5.2669. Min Range: -5.2669

Max Act: 5.2044. Min Act: -0.1700

Data Index: 776044 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 5.2669. Min Range: -5.2669

Max Act: 5.1732. Min Act: -0.1700

Data Index: 304138 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 5.2669. Min Range: -5.2669

Max Act: 5.1107. Min Act: -0.1700

Data Index: 1176859 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 5.2669. Min Range: -5.2669

Max Act: 5.0794. Min Act: -0.1700

Data Index: 638650 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 5.2669. Min Range: -5.2669

Max Act: 4.8919. Min Act: -0.1700

Data Index: 792414 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 5.2669. Min Range: -5.2669

Max Act: 4.9232. Min Act: -0.1700

Data Index: 1200774 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 5.2669. Min Range: -5.2669

Max Act: 4.8607. Min Act: -0.1700

Data Index: 18949 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 5.2669. Min Range: -5.2669

Max Act: 4.7669. Min Act: -0.1700

Data Index: 1285008 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 5.2669. Min Range: -5.2669

Max Act: 4.7982. Min Act: -0.1700

Data Index: 818604 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 5.2669. Min Range: -5.2669

Max Act: 4.7357. Min Act: -0.1700

Data Index: 211803 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 5.2669. Min Range: -5.2669

Max Act: 4.7669. Min Act: -0.1700

Data Index: 674047 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 5.2669. Min Range: -5.2669

Max Act: 4.7982. Min Act: -0.1700

Data Index: 1157787 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 5.2669. Min Range: -5.2669

Max Act: 4.7357. Min Act: -0.1700

Data Index: 546917 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 5.2669. Min Range: -5.2669

Max Act: 4.7357. Min Act: -0.1700

Data Index: 565179 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 5.2669. Min Range: -5.2669

Max Act: 4.7357. Min Act: -0.1700

Data Index: 593555 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 5.2669. Min Range: -5.2669

Max Act: 4.7357. Min Act: -0.1700

Data Index: 317367 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 5.2669. Min Range: -5.2669

Max Act: 4.6732. Min Act: -0.1700

Data Index: 933579 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 5.2669. Min Range: -5.2669

Max Act: 4.6107. Min Act: -0.1700

Data Index: 978426 (C4 (Web Text))

Max Activating Token Index: 701