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

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

Neuron 463 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: 5.4424. Min Range: -5.4424

Max Act: 5.4424. Min Act: -0.1700

Data Index: 9714 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 5.4424. Min Range: -5.4424

Max Act: 5.3487. Min Act: -0.1700

Data Index: 1208437 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 5.4424. Min Range: -5.4424

Max Act: 5.3487. Min Act: -0.1700

Data Index: 616293 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 5.4424. Min Range: -5.4424

Max Act: 5.2862. Min Act: -0.1700

Data Index: 630518 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 5.4424. Min Range: -5.4424

Max Act: 5.3174. Min Act: -0.1700

Data Index: 1135658 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 5.4424. Min Range: -5.4424

Max Act: 5.2549. Min Act: -0.1700

Data Index: 479338 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 5.4424. Min Range: -5.4424

Max Act: 5.2549. Min Act: -0.1700

Data Index: 985487 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 5.4424. Min Range: -5.4424

Max Act: 5.2549. Min Act: -0.1700

Data Index: 1342177 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 5.4424. Min Range: -5.4424

Max Act: 5.2237. Min Act: -0.1700

Data Index: 1202372 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 5.4424. Min Range: -5.4424

Max Act: 5.1612. Min Act: -0.1700

Data Index: 1114031 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 5.4424. Min Range: -5.4424

Max Act: 5.0987. Min Act: -0.1700

Data Index: 999245 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 5.4424. Min Range: -5.4424

Max Act: 5.0674. Min Act: -0.1700

Data Index: 690850 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 5.4424. Min Range: -5.4424

Max Act: 5.0987. Min Act: -0.1700

Data Index: 1189532 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 5.4424. Min Range: -5.4424

Max Act: 5.0362. Min Act: -0.1700

Data Index: 309918 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 5.4424. Min Range: -5.4424

Max Act: 5.0674. Min Act: -0.1700

Data Index: 592675 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 5.4424. Min Range: -5.4424

Max Act: 5.0362. Min Act: -0.1700

Data Index: 267933 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 5.4424. Min Range: -5.4424

Max Act: 5.0362. Min Act: -0.1700

Data Index: 232312 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 5.4424. Min Range: -5.4424

Max Act: 5.0049. Min Act: -0.1700

Data Index: 9867 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 5.4424. Min Range: -5.4424

Max Act: 4.9737. Min Act: -0.1700

Data Index: 736847 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 5.4424. Min Range: -5.4424

Max Act: 5.0049. Min Act: -0.1700

Data Index: 497883 (C4 (Web Text))

Max Activating Token Index: 392