Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 781 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.7067. Min Act: -0.1700

Data Index: 468291 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.6710. Min Act: -0.1700

Data Index: 92796 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.5778. Min Act: -0.1700

Data Index: 1069836 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.6044. Min Act: -0.1700

Data Index: 514996 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.5856. Min Act: -0.1700

Data Index: 769207 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.5497. Min Act: -0.1700

Data Index: 595270 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.5450. Min Act: -0.1700

Data Index: 1275495 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.5591. Min Act: -0.1700

Data Index: 552535 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.5728. Min Act: -0.1700

Data Index: 467537 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.5247. Min Act: -0.1700

Data Index: 1064477 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.5263. Min Act: -0.1700

Data Index: 251300 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.5353. Min Act: -0.1700

Data Index: 956642 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.5186. Min Act: -0.1700

Data Index: 167426 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.5506. Min Act: -0.1700

Data Index: 984445 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.5410. Min Act: -0.1700

Data Index: 1182588 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.5134. Min Act: -0.1700

Data Index: 316942 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.5129. Min Act: -0.1700

Data Index: 304274 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.5165. Min Act: -0.1700

Data Index: 1335796 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.5293. Min Act: -0.1700

Data Index: 870514 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.4969. Min Act: -0.1700

Data Index: 212720 (C4 (Web Text))

Max Activating Token Index: 160