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

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

Neuron 310 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: 3.6894. Min Range: -3.6894

Max Act: 3.6894. Min Act: -0.1700

Data Index: 749051 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.6894. Min Act: -0.1700

Data Index: 161800 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.6424. Min Act: -0.1700

Data Index: 701991 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.6581. Min Act: -0.1700

Data Index: 428545 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.6424. Min Act: -0.1700

Data Index: 1244973 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.6111. Min Act: -0.1700

Data Index: 375152 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.6111. Min Act: -0.1700

Data Index: 674621 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.5798. Min Act: -0.1700

Data Index: 768175 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.5955. Min Act: -0.1700

Data Index: 1335312 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.5328. Min Act: -0.1700

Data Index: 227682 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.5485. Min Act: -0.1700

Data Index: 1333778 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.5485. Min Act: -0.1700

Data Index: 331789 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.4858. Min Act: -0.1700

Data Index: 1184213 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.5328. Min Act: -0.1700

Data Index: 1275866 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.5015. Min Act: -0.1700

Data Index: 1198985 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.5641. Min Act: -0.1700

Data Index: 1230449 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.5172. Min Act: -0.1700

Data Index: 870601 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.5328. Min Act: -0.1700

Data Index: 1093421 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.5172. Min Act: -0.1700

Data Index: 267202 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.4545. Min Act: -0.1700

Data Index: 322226 (C4 (Web Text))

Max Activating Token Index: 204