Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1465 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 8.8491. Min Range: -8.8491

Max Act: 8.8491. Min Act: -0.1700

Data Index: 1220821 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 8.8491. Min Range: -8.8491

Max Act: 8.5679. Min Act: -0.1700

Data Index: 736427 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 8.8491. Min Range: -8.8491

Max Act: 8.3179. Min Act: -0.1700

Data Index: 535381 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 8.8491. Min Range: -8.8491

Max Act: 8.4741. Min Act: -0.1700

Data Index: 74118 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 8.8491. Min Range: -8.8491

Max Act: 8.4116. Min Act: -0.1700

Data Index: 304425 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 8.8491. Min Range: -8.8491

Max Act: 8.3179. Min Act: -0.1699

Data Index: 314849 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 8.8491. Min Range: -8.8491

Max Act: 8.4116. Min Act: -0.1700

Data Index: 496277 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 8.8491. Min Range: -8.8491

Max Act: 8.3804. Min Act: -0.1700

Data Index: 407595 (C4 (Web Text))

Max Activating Token Index: 561

Text #8

Max Range: 8.8491. Min Range: -8.8491

Max Act: 8.2241. Min Act: -0.1700

Data Index: 1117340 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 8.8491. Min Range: -8.8491

Max Act: 8.4741. Min Act: -0.1700

Data Index: 770238 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 8.8491. Min Range: -8.8491

Max Act: 8.5054. Min Act: -0.1700

Data Index: 1080814 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 8.8491. Min Range: -8.8491

Max Act: 8.3179. Min Act: -0.1700

Data Index: 1177396 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 8.8491. Min Range: -8.8491

Max Act: 8.2241. Min Act: -0.1700

Data Index: 202883 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 8.8491. Min Range: -8.8491

Max Act: 8.3491. Min Act: -0.1700

Data Index: 933976 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 8.8491. Min Range: -8.8491

Max Act: 8.2866. Min Act: -0.1700

Data Index: 733261 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 8.8491. Min Range: -8.8491

Max Act: 8.1929. Min Act: -0.1700

Data Index: 357341 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 8.8491. Min Range: -8.8491

Max Act: 7.8804. Min Act: -0.1700

Data Index: 754052 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 8.8491. Min Range: -8.8491

Max Act: 8.2241. Min Act: -0.1700

Data Index: 451076 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 8.8491. Min Range: -8.8491

Max Act: 8.2241. Min Act: -0.1700

Data Index: 701579 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 8.8491. Min Range: -8.8491

Max Act: 8.1616. Min Act: -0.1700

Data Index: 615537 (C4 (Web Text))

Max Activating Token Index: 753