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

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

Neuron 2023 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2309. Min Range: -3.2309

Max Act: 3.2309. Min Act: -0.1700

Data Index: 526524 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 3.2309. Min Range: -3.2309

Max Act: 3.2152. Min Act: -0.1700

Data Index: 1274165 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 3.2309. Min Range: -3.2309

Max Act: 3.1837. Min Act: -0.1700

Data Index: 381458 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 3.2309. Min Range: -3.2309

Max Act: 3.1995. Min Act: -0.1700

Data Index: 994160 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 3.2309. Min Range: -3.2309

Max Act: 3.1365. Min Act: -0.1700

Data Index: 1171206 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 3.2309. Min Range: -3.2309

Max Act: 3.1680. Min Act: -0.1700

Data Index: 976703 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 3.2309. Min Range: -3.2309

Max Act: 3.1365. Min Act: -0.1700

Data Index: 410655 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 3.2309. Min Range: -3.2309

Max Act: 3.1050. Min Act: -0.1700

Data Index: 11090 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 3.2309. Min Range: -3.2309

Max Act: 3.1522. Min Act: -0.1700

Data Index: 468420 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 3.2309. Min Range: -3.2309

Max Act: 3.1365. Min Act: -0.1700

Data Index: 448959 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 3.2309. Min Range: -3.2309

Max Act: 3.1365. Min Act: -0.1700

Data Index: 1274552 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 3.2309. Min Range: -3.2309

Max Act: 3.1050. Min Act: -0.1700

Data Index: 526100 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 3.2309. Min Range: -3.2309

Max Act: 3.1365. Min Act: -0.1700

Data Index: 780419 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 3.2309. Min Range: -3.2309

Max Act: 3.1207. Min Act: -0.1700

Data Index: 719633 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 3.2309. Min Range: -3.2309

Max Act: 3.1207. Min Act: -0.1700

Data Index: 337079 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 3.2309. Min Range: -3.2309

Max Act: 3.1050. Min Act: -0.1700

Data Index: 263694 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 3.2309. Min Range: -3.2309

Max Act: 3.0892. Min Act: -0.1700

Data Index: 1238998 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 3.2309. Min Range: -3.2309

Max Act: 3.0892. Min Act: -0.1700

Data Index: 158357 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 3.2309. Min Range: -3.2309

Max Act: 3.0734. Min Act: -0.1700

Data Index: 269432 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 3.2309. Min Range: -3.2309

Max Act: 3.0734. Min Act: -0.1700

Data Index: 1128195 (C4 (Web Text))

Max Activating Token Index: 8