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

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

Neuron 1953 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: 3.8258. Min Range: -3.8258

Max Act: 3.8258. Min Act: -0.1700

Data Index: 1288492 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.7476. Min Act: -0.1700

Data Index: 481648 (C4 (Web Text))

Max Activating Token Index: 468

Text #2

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.7163. Min Act: -0.1700

Data Index: 1010898 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.6693. Min Act: -0.1700

Data Index: 1351824 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.7163. Min Act: -0.1700

Data Index: 556506 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.6537. Min Act: -0.1700

Data Index: 1087341 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.6537. Min Act: -0.1700

Data Index: 502789 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.6380. Min Act: -0.1700

Data Index: 594834 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.6380. Min Act: -0.1700

Data Index: 87898 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.6224. Min Act: -0.1700

Data Index: 1111742 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.6380. Min Act: -0.1700

Data Index: 149350 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.6067. Min Act: -0.1700

Data Index: 1036991 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.6224. Min Act: -0.1700

Data Index: 685027 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.6067. Min Act: -0.1700

Data Index: 524875 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.6067. Min Act: -0.1700

Data Index: 1137789 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.6537. Min Act: -0.1700

Data Index: 929458 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.5597. Min Act: -0.1700

Data Index: 1138443 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.5754. Min Act: -0.1700

Data Index: 838414 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.5754. Min Act: -0.1700

Data Index: 1133836 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.5284. Min Act: -0.1700

Data Index: 999608 (C4 (Web Text))

Max Activating Token Index: 396