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

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

Neuron 686 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: 3.8129. Min Range: -3.8129

Max Act: 3.8129. Min Act: -0.1700

Data Index: 771238 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.8129. Min Act: -0.1700

Data Index: 336756 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.7503. Min Act: -0.1700

Data Index: 404916 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.6877. Min Act: -0.1700

Data Index: 1326921 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.6877. Min Act: -0.1700

Data Index: 986269 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.5781. Min Act: -0.1700

Data Index: 500072 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.6564. Min Act: -0.1700

Data Index: 923487 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.6094. Min Act: -0.1700

Data Index: 696113 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.5781. Min Act: -0.1700

Data Index: 861800 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.5938. Min Act: -0.1700

Data Index: 1272802 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.5781. Min Act: -0.1700

Data Index: 1322229 (C4 (Web Text))

Max Activating Token Index: 534

Text #11

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.6094. Min Act: -0.1700

Data Index: 316396 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.5468. Min Act: -0.1700

Data Index: 1137149 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.5625. Min Act: -0.1700

Data Index: 1314155 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.5468. Min Act: -0.1700

Data Index: 562022 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.5938. Min Act: -0.1700

Data Index: 313880 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.5625. Min Act: -0.1700

Data Index: 457001 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.5781. Min Act: -0.1700

Data Index: 1353027 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.5625. Min Act: -0.1700

Data Index: 317205 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.5781. Min Act: -0.1700

Data Index: 1066636 (C4 (Web Text))

Max Activating Token Index: 900