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

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

Neuron 363 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: 3.5320. Min Range: -3.5320

Max Act: 3.5320. Min Act: -0.1700

Data Index: 597458 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 3.5320. Min Range: -3.5320

Max Act: 3.5163. Min Act: -0.1700

Data Index: 983901 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 3.5320. Min Range: -3.5320

Max Act: 3.5163. Min Act: -0.1700

Data Index: 1188196 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 3.5320. Min Range: -3.5320

Max Act: 3.4379. Min Act: -0.1700

Data Index: 625716 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 3.5320. Min Range: -3.5320

Max Act: 3.4693. Min Act: -0.1700

Data Index: 760179 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 3.5320. Min Range: -3.5320

Max Act: 3.4379. Min Act: -0.1700

Data Index: 560791 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 3.5320. Min Range: -3.5320

Max Act: 3.4222. Min Act: -0.1700

Data Index: 544921 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 3.5320. Min Range: -3.5320

Max Act: 3.4222. Min Act: -0.1700

Data Index: 500423 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 3.5320. Min Range: -3.5320

Max Act: 3.4536. Min Act: -0.1700

Data Index: 442506 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 3.5320. Min Range: -3.5320

Max Act: 3.3909. Min Act: -0.1700

Data Index: 515879 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 3.5320. Min Range: -3.5320

Max Act: 3.3752. Min Act: -0.1700

Data Index: 1021763 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 3.5320. Min Range: -3.5320

Max Act: 3.3595. Min Act: -0.1700

Data Index: 542090 (C4 (Web Text))

Max Activating Token Index: 617

Text #12

Max Range: 3.5320. Min Range: -3.5320

Max Act: 3.3595. Min Act: -0.1700

Data Index: 753623 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 3.5320. Min Range: -3.5320

Max Act: 3.3909. Min Act: -0.1700

Data Index: 375442 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 3.5320. Min Range: -3.5320

Max Act: 3.3752. Min Act: -0.1700

Data Index: 127199 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 3.5320. Min Range: -3.5320

Max Act: 3.3595. Min Act: -0.1700

Data Index: 549271 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 3.5320. Min Range: -3.5320

Max Act: 3.3595. Min Act: -0.1700

Data Index: 286361 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 3.5320. Min Range: -3.5320

Max Act: 3.3438. Min Act: -0.1700

Data Index: 521210 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 3.5320. Min Range: -3.5320

Max Act: 3.3438. Min Act: -0.1700

Data Index: 254064 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 3.5320. Min Range: -3.5320

Max Act: 3.2967. Min Act: -0.1700

Data Index: 575287 (C4 (Web Text))

Max Activating Token Index: 194