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

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

Neuron 432 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: 5.0961. Min Range: -5.0961

Max Act: 5.0961. Min Act: -0.1700

Data Index: 400172 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 5.0961. Min Range: -5.0961

Max Act: 5.0023. Min Act: -0.1700

Data Index: 836328 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 5.0961. Min Range: -5.0961

Max Act: 5.0023. Min Act: -0.1700

Data Index: 1123850 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 5.0961. Min Range: -5.0961

Max Act: 5.0023. Min Act: -0.1700

Data Index: 1067572 (C4 (Web Text))

Max Activating Token Index: 975

Text #4

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.9398. Min Act: -0.1700

Data Index: 544798 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.9086. Min Act: -0.1700

Data Index: 103477 (C4 (Web Text))

Max Activating Token Index: 396

Text #6

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.9086. Min Act: -0.1700

Data Index: 1269285 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.9086. Min Act: -0.1700

Data Index: 1031877 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.8773. Min Act: -0.1700

Data Index: 640195 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.9086. Min Act: -0.1700

Data Index: 954657 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.9086. Min Act: -0.1700

Data Index: 86870 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.9086. Min Act: -0.1700

Data Index: 461569 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.8773. Min Act: -0.1700

Data Index: 618167 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.8773. Min Act: -0.1700

Data Index: 430945 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.8148. Min Act: -0.1700

Data Index: 872851 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.8773. Min Act: -0.1700

Data Index: 356949 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.8461. Min Act: -0.1700

Data Index: 1310078 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.8148. Min Act: -0.1700

Data Index: 735569 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.8148. Min Act: -0.1700

Data Index: 471349 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.7836. Min Act: -0.1700

Data Index: 241335 (C4 (Web Text))

Max Activating Token Index: 672