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

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

Neuron 510 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: 3.5169. Min Range: -3.5169

Max Act: 3.5169. Min Act: -0.1700

Data Index: 265067 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.5169. Min Act: -0.1700

Data Index: 860680 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.4228. Min Act: -0.1700

Data Index: 1072988 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.4071. Min Act: -0.1700

Data Index: 1191992 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.4071. Min Act: -0.1700

Data Index: 63039 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.3915. Min Act: -0.1700

Data Index: 539582 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.3915. Min Act: -0.1700

Data Index: 1251088 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.3758. Min Act: -0.1700

Data Index: 736125 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.3758. Min Act: -0.1700

Data Index: 346289 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.3758. Min Act: -0.1700

Data Index: 984996 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.3601. Min Act: -0.1700

Data Index: 294201 (C4 (Web Text))

Max Activating Token Index: 385

Text #11

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.3601. Min Act: -0.1700

Data Index: 376716 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.3601. Min Act: -0.1700

Data Index: 621768 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.3601. Min Act: -0.1700

Data Index: 848197 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.3444. Min Act: -0.1700

Data Index: 232675 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.3601. Min Act: -0.1700

Data Index: 515050 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.3444. Min Act: -0.1700

Data Index: 1172368 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.3444. Min Act: -0.1700

Data Index: 28743 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.3444. Min Act: -0.1700

Data Index: 154176 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.3287. Min Act: -0.1700

Data Index: 435100 (C4 (Web Text))

Max Activating Token Index: 707