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

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

Neuron 749 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8907. Min Range: -3.8907

Max Act: 3.8907. Min Act: -0.1700

Data Index: 986504 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 3.8907. Min Range: -3.8907

Max Act: 3.7969. Min Act: -0.1700

Data Index: 781462 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 3.8907. Min Range: -3.8907

Max Act: 3.7969. Min Act: -0.1700

Data Index: 502279 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 3.8907. Min Range: -3.8907

Max Act: 3.7969. Min Act: -0.1700

Data Index: 363694 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 3.8907. Min Range: -3.8907

Max Act: 3.7969. Min Act: -0.1700

Data Index: 257904 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 3.8907. Min Range: -3.8907

Max Act: 3.7969. Min Act: -0.1700

Data Index: 1035576 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 3.8907. Min Range: -3.8907

Max Act: 3.7656. Min Act: -0.1700

Data Index: 1355121 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 3.8907. Min Range: -3.8907

Max Act: 3.7656. Min Act: -0.1700

Data Index: 1266765 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 3.8907. Min Range: -3.8907

Max Act: 3.7343. Min Act: -0.1700

Data Index: 1297179 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 3.8907. Min Range: -3.8907

Max Act: 3.7656. Min Act: -0.1700

Data Index: 127595 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 3.8907. Min Range: -3.8907

Max Act: 3.7343. Min Act: -0.1700

Data Index: 1247247 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 3.8907. Min Range: -3.8907

Max Act: 3.7343. Min Act: -0.1700

Data Index: 725453 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 3.8907. Min Range: -3.8907

Max Act: 3.7343. Min Act: -0.1700

Data Index: 1213692 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 3.8907. Min Range: -3.8907

Max Act: 3.7656. Min Act: -0.1700

Data Index: 498811 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 3.8907. Min Range: -3.8907

Max Act: 3.7656. Min Act: -0.1700

Data Index: 665215 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 3.8907. Min Range: -3.8907

Max Act: 3.7343. Min Act: -0.1700

Data Index: 1235868 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 3.8907. Min Range: -3.8907

Max Act: 3.7030. Min Act: -0.1700

Data Index: 990342 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 3.8907. Min Range: -3.8907

Max Act: 3.6717. Min Act: -0.1700

Data Index: 1117904 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 3.8907. Min Range: -3.8907

Max Act: 3.6717. Min Act: -0.1700

Data Index: 922607 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 3.8907. Min Range: -3.8907

Max Act: 3.6404. Min Act: -0.1700

Data Index: 128723 (C4 (Web Text))

Max Activating Token Index: 823