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

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

Neuron 1302 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: 3.3177. Min Range: -3.3177

Max Act: 3.3020. Min Act: -0.1700

Data Index: 213758 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.3177. Min Act: -0.1700

Data Index: 771709 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.2391. Min Act: -0.1700

Data Index: 635632 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.2549. Min Act: -0.1700

Data Index: 828525 (C4 (Web Text))

Max Activating Token Index: 919

Text #4

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.2391. Min Act: -0.1700

Data Index: 1018059 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.2391. Min Act: -0.1700

Data Index: 698930 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.2391. Min Act: -0.1700

Data Index: 1186930 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1605. Min Act: -0.1700

Data Index: 1314280 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1920. Min Act: -0.1700

Data Index: 650907 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1920. Min Act: -0.1700

Data Index: 1058318 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1920. Min Act: -0.1700

Data Index: 32393 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1605. Min Act: -0.1700

Data Index: 429533 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1762. Min Act: -0.1700

Data Index: 938633 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1762. Min Act: -0.1700

Data Index: 341996 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1605. Min Act: -0.1700

Data Index: 781901 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1605. Min Act: -0.1700

Data Index: 1020248 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1447. Min Act: -0.1700

Data Index: 50879 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1290. Min Act: -0.1700

Data Index: 664200 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1447. Min Act: -0.1700

Data Index: 93421 (C4 (Web Text))

Max Activating Token Index: 2

Text #19

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1447. Min Act: -0.1700

Data Index: 389671 (C4 (Web Text))

Max Activating Token Index: 2