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

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

Neuron 204 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: 3.7984. Min Range: -3.7984

Max Act: 3.7984. Min Act: -0.1700

Data Index: 652432 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.6419. Min Act: -0.1700

Data Index: 394671 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.4853. Min Act: -0.1700

Data Index: 35209 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.4540. Min Act: -0.1700

Data Index: 715762 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.4853. Min Act: -0.1700

Data Index: 68099 (C4 (Web Text))

Max Activating Token Index: 426

Text #5

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.5167. Min Act: -0.1700

Data Index: 832183 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.3913. Min Act: -0.1700

Data Index: 33503 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.3756. Min Act: -0.1700

Data Index: 684522 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.3756. Min Act: -0.1700

Data Index: 68316 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.3756. Min Act: -0.1700

Data Index: 145626 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.3599. Min Act: -0.1700

Data Index: 807977 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.3599. Min Act: -0.1700

Data Index: 1212228 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.3599. Min Act: -0.1700

Data Index: 1101440 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.3442. Min Act: -0.1700

Data Index: 743658 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.3442. Min Act: -0.1700

Data Index: 782409 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.3599. Min Act: -0.1700

Data Index: 308656 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.3599. Min Act: -0.1700

Data Index: 1131503 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.3442. Min Act: -0.1700

Data Index: 287986 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.3599. Min Act: -0.1700

Data Index: 1050513 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.3285. Min Act: -0.1700

Data Index: 152845 (C4 (Web Text))

Max Activating Token Index: 845