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

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

Neuron 157 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.9536. Min Act: -0.1700

Data Index: 75854 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.4536. Min Act: -0.1700

Data Index: 74157 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.3286. Min Act: -0.1700

Data Index: 892557 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.3598. Min Act: -0.1700

Data Index: 1342330 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.3286. Min Act: -0.1700

Data Index: 181319 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.2973. Min Act: -0.1700

Data Index: 407416 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.2348. Min Act: -0.1700

Data Index: 616023 (C4 (Web Text))

Max Activating Token Index: 819

Text #7

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.3286. Min Act: -0.1700

Data Index: 1113156 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.2036. Min Act: -0.1700

Data Index: 209428 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.2348. Min Act: -0.1700

Data Index: 779577 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.2348. Min Act: -0.1700

Data Index: 458102 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.2661. Min Act: -0.1700

Data Index: 156887 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.2348. Min Act: -0.1700

Data Index: 857420 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.2036. Min Act: -0.1700

Data Index: 770267 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.2661. Min Act: -0.1700

Data Index: 308926 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.2348. Min Act: -0.1700

Data Index: 495134 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.1723. Min Act: -0.1700

Data Index: 649666 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.2036. Min Act: -0.1700

Data Index: 1262479 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.2036. Min Act: -0.1700

Data Index: 163502 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.1411. Min Act: -0.1700

Data Index: 959969 (C4 (Web Text))

Max Activating Token Index: 989