Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 561 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.7277. Min Range: -3.7277

Max Act: 3.7277. Min Act: -0.1700

Data Index: 574700 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 3.7277. Min Range: -3.7277

Max Act: 3.6024. Min Act: -0.1700

Data Index: 1134791 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 3.7277. Min Range: -3.7277

Max Act: 3.5711. Min Act: -0.1700

Data Index: 415680 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 3.7277. Min Range: -3.7277

Max Act: 3.5398. Min Act: -0.1700

Data Index: 318946 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 3.7277. Min Range: -3.7277

Max Act: 3.5398. Min Act: -0.1700

Data Index: 409248 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 3.7277. Min Range: -3.7277

Max Act: 3.5555. Min Act: -0.1700

Data Index: 520466 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 3.7277. Min Range: -3.7277

Max Act: 3.5241. Min Act: -0.1700

Data Index: 907880 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 3.7277. Min Range: -3.7277

Max Act: 3.4928. Min Act: -0.1700

Data Index: 237705 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 3.7277. Min Range: -3.7277

Max Act: 3.4771. Min Act: -0.1700

Data Index: 962222 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 3.7277. Min Range: -3.7277

Max Act: 3.4615. Min Act: -0.1700

Data Index: 1058984 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 3.7277. Min Range: -3.7277

Max Act: 3.4615. Min Act: -0.1700

Data Index: 489185 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 3.7277. Min Range: -3.7277

Max Act: 3.4615. Min Act: -0.1700

Data Index: 825834 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 3.7277. Min Range: -3.7277

Max Act: 3.4144. Min Act: -0.1700

Data Index: 1203943 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 3.7277. Min Range: -3.7277

Max Act: 3.4458. Min Act: -0.1700

Data Index: 1093319 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 3.7277. Min Range: -3.7277

Max Act: 3.4458. Min Act: -0.1700

Data Index: 1069920 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 3.7277. Min Range: -3.7277

Max Act: 3.4301. Min Act: -0.1700

Data Index: 178018 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 3.7277. Min Range: -3.7277

Max Act: 3.3987. Min Act: -0.1700

Data Index: 162090 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 3.7277. Min Range: -3.7277

Max Act: 3.4301. Min Act: -0.1700

Data Index: 307576 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 3.7277. Min Range: -3.7277

Max Act: 3.4144. Min Act: -0.1700

Data Index: 333671 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 3.7277. Min Range: -3.7277

Max Act: 3.3987. Min Act: -0.1700

Data Index: 1024780 (C4 (Web Text))

Max Activating Token Index: 1007