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

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

Neuron 1313 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1224. Min Range: -3.1224

Max Act: 3.1224. Min Act: -0.1700

Data Index: 591022 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 3.1224. Min Range: -3.1224

Max Act: 3.0909. Min Act: -0.1700

Data Index: 215471 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 3.1224. Min Range: -3.1224

Max Act: 3.0751. Min Act: -0.1700

Data Index: 1101109 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 3.1224. Min Range: -3.1224

Max Act: 3.0909. Min Act: -0.1700

Data Index: 752000 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 3.1224. Min Range: -3.1224

Max Act: 3.0751. Min Act: -0.1700

Data Index: 1240245 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 3.1224. Min Range: -3.1224

Max Act: 3.0593. Min Act: -0.1700

Data Index: 1024459 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 3.1224. Min Range: -3.1224

Max Act: 3.0436. Min Act: -0.1700

Data Index: 156030 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 3.1224. Min Range: -3.1224

Max Act: 3.0436. Min Act: -0.1700

Data Index: 899015 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 3.1224. Min Range: -3.1224

Max Act: 3.0436. Min Act: -0.1700

Data Index: 620448 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 3.1224. Min Range: -3.1224

Max Act: 3.0278. Min Act: -0.1700

Data Index: 1099240 (C4 (Web Text))

Max Activating Token Index: 1005

Text #10

Max Range: 3.1224. Min Range: -3.1224

Max Act: 3.0120. Min Act: -0.1700

Data Index: 294419 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 3.1224. Min Range: -3.1224

Max Act: 3.0120. Min Act: -0.1700

Data Index: 793000 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 3.1224. Min Range: -3.1224

Max Act: 3.0120. Min Act: -0.1700

Data Index: 1247921 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 3.1224. Min Range: -3.1224

Max Act: 3.0120. Min Act: -0.1700

Data Index: 589100 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.9962. Min Act: -0.1700

Data Index: 1319429 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.9803. Min Act: -0.1700

Data Index: 169127 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.9962. Min Act: -0.1700

Data Index: 1275497 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.9962. Min Act: -0.1700

Data Index: 426479 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.9962. Min Act: -0.1700

Data Index: 204690 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.9803. Min Act: -0.1700

Data Index: 1021517 (C4 (Web Text))

Max Activating Token Index: 75