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

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

Neuron 1297 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8321. Min Range: -5.8321

Max Act: 5.8321. Min Act: -0.1700

Data Index: 22235 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 5.8321. Min Range: -5.8321

Max Act: 5.7696. Min Act: -0.1700

Data Index: 95227 (C4 (Web Text))

Max Activating Token Index: 577

Text #2

Max Range: 5.8321. Min Range: -5.8321

Max Act: 5.6759. Min Act: -0.1700

Data Index: 627785 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 5.8321. Min Range: -5.8321

Max Act: 5.6134. Min Act: -0.1700

Data Index: 432943 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 5.8321. Min Range: -5.8321

Max Act: 5.7384. Min Act: -0.1700

Data Index: 676279 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 5.8321. Min Range: -5.8321

Max Act: 5.5821. Min Act: -0.1700

Data Index: 110018 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 5.8321. Min Range: -5.8321

Max Act: 5.6446. Min Act: -0.1700

Data Index: 1356329 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 5.8321. Min Range: -5.8321

Max Act: 5.5509. Min Act: -0.1700

Data Index: 1339381 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 5.8321. Min Range: -5.8321

Max Act: 5.5196. Min Act: -0.1700

Data Index: 901153 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 5.8321. Min Range: -5.8321

Max Act: 5.5196. Min Act: -0.1700

Data Index: 110112 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 5.8321. Min Range: -5.8321

Max Act: 5.4884. Min Act: -0.1700

Data Index: 290222 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 5.8321. Min Range: -5.8321

Max Act: 5.5509. Min Act: -0.1700

Data Index: 804998 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 5.8321. Min Range: -5.8321

Max Act: 5.4884. Min Act: -0.1700

Data Index: 197898 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 5.8321. Min Range: -5.8321

Max Act: 5.3946. Min Act: -0.1700

Data Index: 297456 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 5.8321. Min Range: -5.8321

Max Act: 5.4259. Min Act: -0.1700

Data Index: 1265233 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 5.8321. Min Range: -5.8321

Max Act: 5.3009. Min Act: -0.1700

Data Index: 1005635 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 5.8321. Min Range: -5.8321

Max Act: 5.3946. Min Act: -0.1700

Data Index: 853498 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 5.8321. Min Range: -5.8321

Max Act: 5.3946. Min Act: -0.1700

Data Index: 511836 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 5.8321. Min Range: -5.8321

Max Act: 5.4571. Min Act: -0.1700

Data Index: 117210 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 5.8321. Min Range: -5.8321

Max Act: 5.3009. Min Act: -0.1700

Data Index: 1107030 (C4 (Web Text))

Max Activating Token Index: 220