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

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

Neuron 120 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0029. Min Range: -4.0029

Max Act: 4.0029. Min Act: -0.1700

Data Index: 870175 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.9717. Min Act: -0.1700

Data Index: 170171 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.8779. Min Act: -0.1700

Data Index: 583852 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.8779. Min Act: -0.1700

Data Index: 754562 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.8466. Min Act: -0.1700

Data Index: 52300 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.7997. Min Act: -0.1700

Data Index: 526835 (C4 (Web Text))

Max Activating Token Index: 979

Text #6

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.7684. Min Act: -0.1700

Data Index: 818840 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.7527. Min Act: -0.1700

Data Index: 114097 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.7527. Min Act: -0.1700

Data Index: 437967 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.6902. Min Act: -0.1700

Data Index: 28900 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.7371. Min Act: -0.1700

Data Index: 142870 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.7058. Min Act: -0.1700

Data Index: 436089 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.7058. Min Act: -0.1700

Data Index: 1049372 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.7215. Min Act: -0.1700

Data Index: 327393 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.6432. Min Act: -0.1700

Data Index: 724327 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.6902. Min Act: -0.1700

Data Index: 52071 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.7058. Min Act: -0.1700

Data Index: 652440 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.7215. Min Act: -0.1700

Data Index: 1022286 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.7215. Min Act: -0.1700

Data Index: 929848 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.6902. Min Act: -0.1700

Data Index: 757943 (C4 (Web Text))

Max Activating Token Index: 147