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

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

Neuron 1092 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: 5.1274. Min Range: -5.1274

Max Act: 5.1274. Min Act: -0.1700

Data Index: 532975 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.8461. Min Act: -0.1700

Data Index: 526093 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.7836. Min Act: -0.1700

Data Index: 609184 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.8149. Min Act: -0.1700

Data Index: 366816 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.6899. Min Act: -0.1700

Data Index: 550703 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.6586. Min Act: -0.1700

Data Index: 689926 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.6586. Min Act: -0.1700

Data Index: 794648 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.6899. Min Act: -0.1700

Data Index: 563115 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.6274. Min Act: -0.1700

Data Index: 1047442 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.6586. Min Act: -0.1700

Data Index: 121561 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.5961. Min Act: -0.1700

Data Index: 376316 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.5649. Min Act: -0.1700

Data Index: 935302 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.5649. Min Act: -0.1700

Data Index: 1066277 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.4399. Min Act: -0.1700

Data Index: 161784 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.5649. Min Act: -0.1700

Data Index: 314595 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.4399. Min Act: -0.1700

Data Index: 721134 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.5336. Min Act: -0.1700

Data Index: 614576 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.4711. Min Act: -0.1700

Data Index: 325435 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.4711. Min Act: -0.1700

Data Index: 632430 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.4711. Min Act: -0.1700

Data Index: 986180 (C4 (Web Text))

Max Activating Token Index: 91