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

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

Neuron 1295 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: 3.2552. Min Range: -3.2552

Max Act: 3.2552. Min Act: -0.1700

Data Index: 764632 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 3.2552. Min Range: -3.2552

Max Act: 3.2395. Min Act: -0.1700

Data Index: 930744 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 3.2552. Min Range: -3.2552

Max Act: 3.2080. Min Act: -0.1700

Data Index: 336800 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 3.2552. Min Range: -3.2552

Max Act: 3.1923. Min Act: -0.1700

Data Index: 1236537 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 3.2552. Min Range: -3.2552

Max Act: 3.1608. Min Act: -0.1700

Data Index: 555571 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 3.2552. Min Range: -3.2552

Max Act: 3.1293. Min Act: -0.1700

Data Index: 1097470 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 3.2552. Min Range: -3.2552

Max Act: 3.1293. Min Act: -0.1700

Data Index: 1313148 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 3.2552. Min Range: -3.2552

Max Act: 3.1136. Min Act: -0.1700

Data Index: 360305 (C4 (Web Text))

Max Activating Token Index: 776

Text #8

Max Range: 3.2552. Min Range: -3.2552

Max Act: 3.1136. Min Act: -0.1700

Data Index: 2979 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 3.2552. Min Range: -3.2552

Max Act: 3.0978. Min Act: -0.1700

Data Index: 1315518 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 3.2552. Min Range: -3.2552

Max Act: 3.0978. Min Act: -0.1700

Data Index: 259529 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 3.2552. Min Range: -3.2552

Max Act: 3.0978. Min Act: -0.1700

Data Index: 1193488 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 3.2552. Min Range: -3.2552

Max Act: 3.0820. Min Act: -0.1700

Data Index: 711558 (C4 (Web Text))

Max Activating Token Index: 261

Text #13

Max Range: 3.2552. Min Range: -3.2552

Max Act: 3.0978. Min Act: -0.1700

Data Index: 919969 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 3.2552. Min Range: -3.2552

Max Act: 3.0820. Min Act: -0.1700

Data Index: 859142 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 3.2552. Min Range: -3.2552

Max Act: 3.0663. Min Act: -0.1700

Data Index: 993030 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 3.2552. Min Range: -3.2552

Max Act: 3.0505. Min Act: -0.1700

Data Index: 643247 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 3.2552. Min Range: -3.2552

Max Act: 3.0663. Min Act: -0.1700

Data Index: 1154856 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 3.2552. Min Range: -3.2552

Max Act: 3.0505. Min Act: -0.1700

Data Index: 268199 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 3.2552. Min Range: -3.2552

Max Act: 3.0505. Min Act: -0.1700

Data Index: 228912 (C4 (Web Text))

Max Activating Token Index: 223