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

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

Neuron 870 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: 3.8784. Min Range: -3.8784

Max Act: 3.8784. Min Act: -0.1700

Data Index: 77861 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 3.8784. Min Range: -3.8784

Max Act: 3.8471. Min Act: -0.1700

Data Index: 601940 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 3.8784. Min Range: -3.8784

Max Act: 3.8471. Min Act: -0.1700

Data Index: 578882 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 3.8784. Min Range: -3.8784

Max Act: 3.8315. Min Act: -0.1700

Data Index: 21056 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 3.8784. Min Range: -3.8784

Max Act: 3.8315. Min Act: -0.1700

Data Index: 548677 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 3.8784. Min Range: -3.8784

Max Act: 3.8315. Min Act: -0.1700

Data Index: 944172 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 3.8784. Min Range: -3.8784

Max Act: 3.7845. Min Act: -0.1700

Data Index: 742535 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 3.8784. Min Range: -3.8784

Max Act: 3.7845. Min Act: -0.1700

Data Index: 1341021 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 3.8784. Min Range: -3.8784

Max Act: 3.7845. Min Act: -0.1700

Data Index: 1325763 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 3.8784. Min Range: -3.8784

Max Act: 3.7845. Min Act: -0.1700

Data Index: 244864 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 3.8784. Min Range: -3.8784

Max Act: 3.7845. Min Act: -0.1700

Data Index: 174823 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 3.8784. Min Range: -3.8784

Max Act: 3.8002. Min Act: -0.1700

Data Index: 1207140 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 3.8784. Min Range: -3.8784

Max Act: 3.7689. Min Act: -0.1700

Data Index: 931892 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 3.8784. Min Range: -3.8784

Max Act: 3.7533. Min Act: -0.1700

Data Index: 631021 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 3.8784. Min Range: -3.8784

Max Act: 3.7689. Min Act: -0.1700

Data Index: 814866 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 3.8784. Min Range: -3.8784

Max Act: 3.7533. Min Act: -0.1700

Data Index: 1127566 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 3.8784. Min Range: -3.8784

Max Act: 3.7376. Min Act: -0.1700

Data Index: 859932 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 3.8784. Min Range: -3.8784

Max Act: 3.7376. Min Act: -0.1700

Data Index: 132214 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 3.8784. Min Range: -3.8784

Max Act: 3.7220. Min Act: -0.1700

Data Index: 950782 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 3.8784. Min Range: -3.8784

Max Act: 3.7220. Min Act: -0.1700

Data Index: 1103564 (C4 (Web Text))

Max Activating Token Index: 648