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

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

Neuron 1684 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: 3.9391. Min Range: -3.9391

Max Act: 3.9391. Min Act: -0.1700

Data Index: 227494 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.6263. Min Act: -0.1700

Data Index: 740047 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.6263. Min Act: -0.1700

Data Index: 1221678 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.6263. Min Act: -0.1700

Data Index: 1050326 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.5636. Min Act: -0.1700

Data Index: 446708 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.5636. Min Act: -0.1700

Data Index: 856975 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.5636. Min Act: -0.1700

Data Index: 148971 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.5010. Min Act: -0.1700

Data Index: 283199 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.5010. Min Act: -0.1700

Data Index: 493792 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.5323. Min Act: -0.1700

Data Index: 270357 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.5010. Min Act: -0.1700

Data Index: 696466 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.5010. Min Act: -0.1700

Data Index: 899524 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.4696. Min Act: -0.1700

Data Index: 1181501 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.4696. Min Act: -0.1700

Data Index: 218224 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.4696. Min Act: -0.1700

Data Index: 466649 (C4 (Web Text))

Max Activating Token Index: 117

Text #15

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.5010. Min Act: -0.1700

Data Index: 863460 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.4069. Min Act: -0.1700

Data Index: 502315 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.4696. Min Act: -0.1700

Data Index: 662244 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.4069. Min Act: -0.1700

Data Index: 73990 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.4383. Min Act: -0.1700

Data Index: 789390 (C4 (Web Text))

Max Activating Token Index: 669