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

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

Neuron 1967 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: 5.4855. Min Range: -5.4855

Max Act: 5.4855. Min Act: -0.1700

Data Index: 437423 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 5.4855. Min Range: -5.4855

Max Act: 5.3292. Min Act: -0.1700

Data Index: 800243 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 5.4855. Min Range: -5.4855

Max Act: 5.3605. Min Act: -0.1700

Data Index: 672590 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 5.4855. Min Range: -5.4855

Max Act: 5.2042. Min Act: -0.1700

Data Index: 134996 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 5.4855. Min Range: -5.4855

Max Act: 5.2042. Min Act: -0.1700

Data Index: 1131923 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 5.4855. Min Range: -5.4855

Max Act: 5.2355. Min Act: -0.1700

Data Index: 418387 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 5.4855. Min Range: -5.4855

Max Act: 5.2042. Min Act: -0.1700

Data Index: 1341109 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 5.4855. Min Range: -5.4855

Max Act: 5.1730. Min Act: -0.1700

Data Index: 1319032 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 5.4855. Min Range: -5.4855

Max Act: 5.2042. Min Act: -0.1700

Data Index: 593237 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 5.4855. Min Range: -5.4855

Max Act: 5.1730. Min Act: -0.1700

Data Index: 457045 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 5.4855. Min Range: -5.4855

Max Act: 5.2042. Min Act: -0.1700

Data Index: 321465 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 5.4855. Min Range: -5.4855

Max Act: 5.1105. Min Act: -0.1700

Data Index: 255969 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 5.4855. Min Range: -5.4855

Max Act: 5.1105. Min Act: -0.1700

Data Index: 200573 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 5.4855. Min Range: -5.4855

Max Act: 5.1730. Min Act: -0.1700

Data Index: 1126248 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 5.4855. Min Range: -5.4855

Max Act: 5.0792. Min Act: -0.1700

Data Index: 81981 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 5.4855. Min Range: -5.4855

Max Act: 5.0480. Min Act: -0.1700

Data Index: 1201574 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 5.4855. Min Range: -5.4855

Max Act: 5.0480. Min Act: -0.1700

Data Index: 873284 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 5.4855. Min Range: -5.4855

Max Act: 5.1105. Min Act: -0.1700

Data Index: 207752 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 5.4855. Min Range: -5.4855

Max Act: 5.0480. Min Act: -0.1700

Data Index: 763509 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 5.4855. Min Range: -5.4855

Max Act: 5.0167. Min Act: -0.1700

Data Index: 1095078 (C4 (Web Text))

Max Activating Token Index: 624