Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1054 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.0750. Min Range: -3.0750

Max Act: 3.0750. Min Act: -0.1700

Data Index: 200086 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 3.0750. Min Range: -3.0750

Max Act: 3.0434. Min Act: -0.1700

Data Index: 1005618 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 3.0750. Min Range: -3.0750

Max Act: 3.0434. Min Act: -0.1700

Data Index: 1178732 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 3.0750. Min Range: -3.0750

Max Act: 3.0118. Min Act: -0.1700

Data Index: 212340 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 3.0750. Min Range: -3.0750

Max Act: 3.0118. Min Act: -0.1700

Data Index: 474461 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 3.0750. Min Range: -3.0750

Max Act: 3.0118. Min Act: -0.1700

Data Index: 967181 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 3.0750. Min Range: -3.0750

Max Act: 3.0118. Min Act: -0.1700

Data Index: 560931 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 3.0750. Min Range: -3.0750

Max Act: 2.9960. Min Act: -0.1700

Data Index: 982073 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 3.0750. Min Range: -3.0750

Max Act: 2.9960. Min Act: -0.1700

Data Index: 723343 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 3.0750. Min Range: -3.0750

Max Act: 2.8534. Min Act: -0.1700

Data Index: 690407 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 3.0750. Min Range: -3.0750

Max Act: 2.8057. Min Act: -0.1700

Data Index: 199710 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 3.0750. Min Range: -3.0750

Max Act: 2.7897. Min Act: -0.1700

Data Index: 590057 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 3.0750. Min Range: -3.0750

Max Act: 2.7738. Min Act: -0.1700

Data Index: 969188 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 3.0750. Min Range: -3.0750

Max Act: 2.7579. Min Act: -0.1700

Data Index: 40040 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 3.0750. Min Range: -3.0750

Max Act: 2.7099. Min Act: -0.1700

Data Index: 804856 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 3.0750. Min Range: -3.0750

Max Act: 2.6939. Min Act: -0.1700

Data Index: 185989 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 3.0750. Min Range: -3.0750

Max Act: 2.6779. Min Act: -0.1700

Data Index: 1358117 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 3.0750. Min Range: -3.0750

Max Act: 2.6619. Min Act: -0.1700

Data Index: 136211 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 3.0750. Min Range: -3.0750

Max Act: 2.6298. Min Act: -0.1700

Data Index: 1261257 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 3.0750. Min Range: -3.0750

Max Act: 2.6458. Min Act: -0.1700

Data Index: 164953 (C4 (Web Text))

Max Activating Token Index: 400