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

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

Neuron 1875 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: 5.4094. Min Range: -5.4094

Max Act: 5.4094. Min Act: -0.1700

Data Index: 557183 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 5.4094. Min Range: -5.4094

Max Act: 5.3781. Min Act: -0.1700

Data Index: 99807 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 5.4094. Min Range: -5.4094

Max Act: 5.2531. Min Act: -0.1700

Data Index: 986772 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 5.4094. Min Range: -5.4094

Max Act: 5.1594. Min Act: -0.1700

Data Index: 1073939 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 5.4094. Min Range: -5.4094

Max Act: 5.1594. Min Act: -0.1700

Data Index: 1261145 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 5.4094. Min Range: -5.4094

Max Act: 5.1281. Min Act: -0.1700

Data Index: 833822 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 5.4094. Min Range: -5.4094

Max Act: 5.2219. Min Act: -0.1700

Data Index: 1109089 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 5.4094. Min Range: -5.4094

Max Act: 5.1281. Min Act: -0.1700

Data Index: 108791 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 5.4094. Min Range: -5.4094

Max Act: 5.1594. Min Act: -0.1700

Data Index: 374031 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 5.4094. Min Range: -5.4094

Max Act: 5.1281. Min Act: -0.1700

Data Index: 709715 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 5.4094. Min Range: -5.4094

Max Act: 5.0969. Min Act: -0.1700

Data Index: 736427 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 5.4094. Min Range: -5.4094

Max Act: 5.0969. Min Act: -0.1700

Data Index: 41199 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 5.4094. Min Range: -5.4094

Max Act: 5.1281. Min Act: -0.1700

Data Index: 203023 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 5.4094. Min Range: -5.4094

Max Act: 5.1281. Min Act: -0.1700

Data Index: 83774 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 5.4094. Min Range: -5.4094

Max Act: 5.1281. Min Act: -0.1700

Data Index: 468927 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 5.4094. Min Range: -5.4094

Max Act: 5.1281. Min Act: -0.1700

Data Index: 1199883 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 5.4094. Min Range: -5.4094

Max Act: 5.1281. Min Act: -0.1700

Data Index: 1204535 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 5.4094. Min Range: -5.4094

Max Act: 5.0969. Min Act: -0.1700

Data Index: 720796 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 5.4094. Min Range: -5.4094

Max Act: 5.0656. Min Act: -0.1700

Data Index: 935101 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 5.4094. Min Range: -5.4094

Max Act: 5.0656. Min Act: -0.1700

Data Index: 288637 (C4 (Web Text))

Max Activating Token Index: 170