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

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

Neuron 673 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: 3.7434. Min Range: -3.7434

Max Act: 3.7434. Min Act: -0.1700

Data Index: 597139 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.5869. Min Act: -0.1700

Data Index: 725019 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.5555. Min Act: -0.1700

Data Index: 974966 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.5555. Min Act: -0.1700

Data Index: 1012098 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.5555. Min Act: -0.1700

Data Index: 1152078 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.4929. Min Act: -0.1700

Data Index: 1523902 (Python Code)

Max Activating Token Index: 665

Text #6

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.4772. Min Act: -0.1700

Data Index: 647903 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.4772. Min Act: -0.1700

Data Index: 758553 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.4459. Min Act: -0.1700

Data Index: 725170 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.4145. Min Act: -0.1700

Data Index: 572915 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.4302. Min Act: -0.1700

Data Index: 375700 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.3831. Min Act: -0.1700

Data Index: 1002100 (C4 (Web Text))

Max Activating Token Index: 525

Text #12

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.3674. Min Act: -0.1700

Data Index: 705225 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.4302. Min Act: -0.1700

Data Index: 832181 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.3988. Min Act: -0.1700

Data Index: 699939 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.3831. Min Act: -0.1700

Data Index: 1354286 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.3831. Min Act: -0.1700

Data Index: 412467 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.3831. Min Act: -0.1700

Data Index: 32424 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.3831. Min Act: -0.1700

Data Index: 1478798 (Python Code)

Max Activating Token Index: 675

Text #19

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.3517. Min Act: -0.1700

Data Index: 973850 (C4 (Web Text))

Max Activating Token Index: 609