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

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

Neuron 1542 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0113. Min Range: -5.0113

Max Act: 4.9801. Min Act: -0.1700

Data Index: 37984 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 5.0113. Min Range: -5.0113

Max Act: 5.0113. Min Act: -0.1700

Data Index: 990031 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 5.0113. Min Range: -5.0113

Max Act: 4.9801. Min Act: -0.1700

Data Index: 859705 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 5.0113. Min Range: -5.0113

Max Act: 4.8863. Min Act: -0.1700

Data Index: 861141 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 5.0113. Min Range: -5.0113

Max Act: 4.8238. Min Act: -0.1700

Data Index: 76197 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 5.0113. Min Range: -5.0113

Max Act: 4.8238. Min Act: -0.1700

Data Index: 1117156 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 5.0113. Min Range: -5.0113

Max Act: 4.7613. Min Act: -0.1700

Data Index: 687964 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 5.0113. Min Range: -5.0113

Max Act: 4.7926. Min Act: -0.1656

Data Index: 665860 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 5.0113. Min Range: -5.0113

Max Act: 4.7301. Min Act: -0.1700

Data Index: 1252475 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 5.0113. Min Range: -5.0113

Max Act: 4.7301. Min Act: -0.1682

Data Index: 1306183 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 5.0113. Min Range: -5.0113

Max Act: 4.6676. Min Act: -0.1700

Data Index: 545620 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 5.0113. Min Range: -5.0113

Max Act: 4.7301. Min Act: -0.1700

Data Index: 1174042 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 5.0113. Min Range: -5.0113

Max Act: 4.7301. Min Act: -0.1700

Data Index: 502017 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 5.0113. Min Range: -5.0113

Max Act: 4.6988. Min Act: -0.1700

Data Index: 598468 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 5.0113. Min Range: -5.0113

Max Act: 4.6676. Min Act: -0.1700

Data Index: 1020111 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 5.0113. Min Range: -5.0113

Max Act: 4.6363. Min Act: -0.1700

Data Index: 846694 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 5.0113. Min Range: -5.0113

Max Act: 4.6363. Min Act: -0.1700

Data Index: 807788 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 5.0113. Min Range: -5.0113

Max Act: 4.6051. Min Act: -0.1700

Data Index: 1034375 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 5.0113. Min Range: -5.0113

Max Act: 4.6051. Min Act: -0.1700

Data Index: 1316269 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 5.0113. Min Range: -5.0113

Max Act: 4.5738. Min Act: -0.1700

Data Index: 367644 (C4 (Web Text))

Max Activating Token Index: 79