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

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

Neuron 413 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: 7.3883. Min Range: -7.3883

Max Act: 7.3883. Min Act: -0.1700

Data Index: 173230 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 7.3883. Min Range: -7.3883

Max Act: 7.3258. Min Act: -0.1700

Data Index: 760133 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 7.3883. Min Range: -7.3883

Max Act: 7.2633. Min Act: -0.1700

Data Index: 375332 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 7.3883. Min Range: -7.3883

Max Act: 7.1695. Min Act: -0.1700

Data Index: 1086720 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 7.3883. Min Range: -7.3883

Max Act: 7.1383. Min Act: -0.1700

Data Index: 461075 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 7.3883. Min Range: -7.3883

Max Act: 6.8570. Min Act: -0.1700

Data Index: 1142576 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 7.3883. Min Range: -7.3883

Max Act: 6.8258. Min Act: -0.1700

Data Index: 286183 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 7.3883. Min Range: -7.3883

Max Act: 6.7945. Min Act: -0.1700

Data Index: 109352 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 7.3883. Min Range: -7.3883

Max Act: 6.8258. Min Act: -0.1700

Data Index: 924085 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 7.3883. Min Range: -7.3883

Max Act: 6.7945. Min Act: -0.1700

Data Index: 366336 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 7.3883. Min Range: -7.3883

Max Act: 6.7945. Min Act: -0.1700

Data Index: 200134 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 7.3883. Min Range: -7.3883

Max Act: 6.7945. Min Act: -0.1700

Data Index: 1168257 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 7.3883. Min Range: -7.3883

Max Act: 6.7320. Min Act: -0.1700

Data Index: 1064878 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 7.3883. Min Range: -7.3883

Max Act: 6.7008. Min Act: -0.1700

Data Index: 1266906 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 7.3883. Min Range: -7.3883

Max Act: 6.7320. Min Act: -0.1700

Data Index: 1091161 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 7.3883. Min Range: -7.3883

Max Act: 6.7008. Min Act: -0.1700

Data Index: 77913 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 7.3883. Min Range: -7.3883

Max Act: 6.6695. Min Act: -0.1700

Data Index: 1228418 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 7.3883. Min Range: -7.3883

Max Act: 6.7008. Min Act: -0.1700

Data Index: 421257 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 7.3883. Min Range: -7.3883

Max Act: 6.6070. Min Act: -0.1700

Data Index: 430567 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 7.3883. Min Range: -7.3883

Max Act: 6.6695. Min Act: -0.1700

Data Index: 1125013 (C4 (Web Text))

Max Activating Token Index: 222