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

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

Neuron 1495 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9189. Min Range: -3.9189

Max Act: 3.9189. Min Act: -0.1700

Data Index: 866836 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 3.9189. Min Range: -3.9189

Max Act: 3.8251. Min Act: -0.1700

Data Index: 967061 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 3.9189. Min Range: -3.9189

Max Act: 3.8876. Min Act: -0.1700

Data Index: 1165764 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 3.9189. Min Range: -3.9189

Max Act: 3.8251. Min Act: -0.1700

Data Index: 665424 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 3.9189. Min Range: -3.9189

Max Act: 3.8251. Min Act: -0.1700

Data Index: 847113 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 3.9189. Min Range: -3.9189

Max Act: 3.8564. Min Act: -0.1700

Data Index: 99089 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 3.9189. Min Range: -3.9189

Max Act: 3.8251. Min Act: -0.1700

Data Index: 1240620 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 3.9189. Min Range: -3.9189

Max Act: 3.8251. Min Act: -0.1700

Data Index: 639941 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 3.9189. Min Range: -3.9189

Max Act: 3.8564. Min Act: -0.1700

Data Index: 1185453 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 3.9189. Min Range: -3.9189

Max Act: 3.8251. Min Act: -0.1700

Data Index: 650033 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 3.9189. Min Range: -3.9189

Max Act: 3.7938. Min Act: -0.1700

Data Index: 317214 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 3.9189. Min Range: -3.9189

Max Act: 3.7625. Min Act: -0.1700

Data Index: 253119 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 3.9189. Min Range: -3.9189

Max Act: 3.7625. Min Act: -0.1700

Data Index: 311539 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 3.9189. Min Range: -3.9189

Max Act: 3.7938. Min Act: -0.1700

Data Index: 293050 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 3.9189. Min Range: -3.9189

Max Act: 3.8251. Min Act: -0.1700

Data Index: 1202954 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 3.9189. Min Range: -3.9189

Max Act: 3.7312. Min Act: -0.1700

Data Index: 824811 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 3.9189. Min Range: -3.9189

Max Act: 3.7938. Min Act: -0.1700

Data Index: 794585 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 3.9189. Min Range: -3.9189

Max Act: 3.8251. Min Act: -0.1700

Data Index: 145077 (C4 (Web Text))

Max Activating Token Index: 526

Text #18

Max Range: 3.9189. Min Range: -3.9189

Max Act: 3.8251. Min Act: -0.1700

Data Index: 692136 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 3.9189. Min Range: -3.9189

Max Act: 3.8564. Min Act: -0.1700

Data Index: 663708 (C4 (Web Text))

Max Activating Token Index: 45