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

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

Neuron 808 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: 5.0380. Min Range: -5.0380

Max Act: 5.0380. Min Act: -0.1700

Data Index: 1149124 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 5.0380. Min Range: -5.0380

Max Act: 4.9130. Min Act: -0.1700

Data Index: 432517 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 5.0380. Min Range: -5.0380

Max Act: 4.8505. Min Act: -0.1700

Data Index: 463142 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 5.0380. Min Range: -5.0380

Max Act: 4.8818. Min Act: -0.1700

Data Index: 422221 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 5.0380. Min Range: -5.0380

Max Act: 4.8193. Min Act: -0.1700

Data Index: 427216 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 5.0380. Min Range: -5.0380

Max Act: 4.8193. Min Act: -0.1700

Data Index: 219216 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 5.0380. Min Range: -5.0380

Max Act: 4.7568. Min Act: -0.1700

Data Index: 1272646 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 5.0380. Min Range: -5.0380

Max Act: 4.7255. Min Act: -0.1700

Data Index: 458133 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 5.0380. Min Range: -5.0380

Max Act: 4.7255. Min Act: -0.1700

Data Index: 553816 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 5.0380. Min Range: -5.0380

Max Act: 4.6943. Min Act: -0.1700

Data Index: 1291107 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 5.0380. Min Range: -5.0380

Max Act: 4.6630. Min Act: -0.1700

Data Index: 570758 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 5.0380. Min Range: -5.0380

Max Act: 4.6318. Min Act: -0.1700

Data Index: 134014 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 5.0380. Min Range: -5.0380

Max Act: 4.6943. Min Act: -0.1700

Data Index: 430723 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 5.0380. Min Range: -5.0380

Max Act: 4.6630. Min Act: -0.1698

Data Index: 1358333 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 5.0380. Min Range: -5.0380

Max Act: 4.6318. Min Act: -0.1700

Data Index: 231388 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 5.0380. Min Range: -5.0380

Max Act: 4.6005. Min Act: -0.1700

Data Index: 927420 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 5.0380. Min Range: -5.0380

Max Act: 4.6630. Min Act: -0.1700

Data Index: 941340 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 5.0380. Min Range: -5.0380

Max Act: 4.6318. Min Act: -0.1700

Data Index: 485156 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 5.0380. Min Range: -5.0380

Max Act: 4.6005. Min Act: -0.1700

Data Index: 1047280 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 5.0380. Min Range: -5.0380

Max Act: 4.6005. Min Act: -0.1700

Data Index: 175117 (C4 (Web Text))

Max Activating Token Index: 272