Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 317 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.2962. Min Range: -5.2962

Max Act: 5.2650. Min Act: -0.1700

Data Index: 742279 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 5.2962. Min Range: -5.2962

Max Act: 5.2962. Min Act: -0.1700

Data Index: 1085039 (C4 (Web Text))

Max Activating Token Index: 225

Text #2

Max Range: 5.2962. Min Range: -5.2962

Max Act: 5.2337. Min Act: -0.1700

Data Index: 445340 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 5.2962. Min Range: -5.2962

Max Act: 5.1712. Min Act: -0.1700

Data Index: 180896 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 5.2962. Min Range: -5.2962

Max Act: 5.1712. Min Act: -0.1700

Data Index: 301325 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 5.2962. Min Range: -5.2962

Max Act: 5.2025. Min Act: -0.1700

Data Index: 1006753 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 5.2962. Min Range: -5.2962

Max Act: 5.1087. Min Act: -0.1700

Data Index: 1216670 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 5.2962. Min Range: -5.2962

Max Act: 5.0775. Min Act: -0.1700

Data Index: 541600 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 5.2962. Min Range: -5.2962

Max Act: 5.0150. Min Act: -0.1700

Data Index: 270161 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 5.2962. Min Range: -5.2962

Max Act: 5.1712. Min Act: -0.1700

Data Index: 742966 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 5.2962. Min Range: -5.2962

Max Act: 5.1087. Min Act: -0.1700

Data Index: 845050 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 5.2962. Min Range: -5.2962

Max Act: 5.1087. Min Act: -0.1700

Data Index: 997908 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 5.2962. Min Range: -5.2962

Max Act: 5.0775. Min Act: -0.1700

Data Index: 228718 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 5.2962. Min Range: -5.2962

Max Act: 5.1087. Min Act: -0.1700

Data Index: 296015 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 5.2962. Min Range: -5.2962

Max Act: 4.9525. Min Act: -0.1700

Data Index: 632128 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 5.2962. Min Range: -5.2962

Max Act: 5.0150. Min Act: -0.1700

Data Index: 169780 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 5.2962. Min Range: -5.2962

Max Act: 4.9525. Min Act: -0.1700

Data Index: 267669 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 5.2962. Min Range: -5.2962

Max Act: 5.0150. Min Act: -0.1700

Data Index: 127941 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 5.2962. Min Range: -5.2962

Max Act: 5.0462. Min Act: -0.1700

Data Index: 985279 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 5.2962. Min Range: -5.2962

Max Act: 5.0462. Min Act: -0.1700

Data Index: 1204207 (C4 (Web Text))

Max Activating Token Index: 221