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

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

Neuron 185 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: 4.8220. Min Range: -4.8220

Max Act: 4.8220. Min Act: -0.1700

Data Index: 1072576 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 4.8220. Min Range: -4.8220

Max Act: 4.6562. Min Act: -0.1700

Data Index: 320928 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 4.8220. Min Range: -4.8220

Max Act: 4.6020. Min Act: -0.1700

Data Index: 456719 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 4.8220. Min Range: -4.8220

Max Act: 4.5983. Min Act: -0.1700

Data Index: 1299624 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 4.8220. Min Range: -4.8220

Max Act: 4.5047. Min Act: -0.1700

Data Index: 897613 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 4.8220. Min Range: -4.8220

Max Act: 4.5034. Min Act: -0.1700

Data Index: 680233 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 4.8220. Min Range: -4.8220

Max Act: 4.4624. Min Act: -0.1700

Data Index: 1290086 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 4.8220. Min Range: -4.8220

Max Act: 4.4910. Min Act: -0.1700

Data Index: 179836 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 4.8220. Min Range: -4.8220

Max Act: 4.4336. Min Act: -0.1700

Data Index: 1216830 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 4.8220. Min Range: -4.8220

Max Act: 4.4020. Min Act: -0.1699

Data Index: 923533 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 4.8220. Min Range: -4.8220

Max Act: 4.3962. Min Act: -0.1700

Data Index: 205259 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 4.8220. Min Range: -4.8220

Max Act: 4.4141. Min Act: -0.1700

Data Index: 1064790 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 4.8220. Min Range: -4.8220

Max Act: 4.3561. Min Act: -0.1700

Data Index: 1085522 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 4.8220. Min Range: -4.8220

Max Act: 4.3552. Min Act: -0.1700

Data Index: 888100 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 4.8220. Min Range: -4.8220

Max Act: 4.3004. Min Act: -0.1700

Data Index: 953696 (C4 (Web Text))

Max Activating Token Index: 465

Text #15

Max Range: 4.8220. Min Range: -4.8220

Max Act: 4.3127. Min Act: -0.1700

Data Index: 18040 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 4.8220. Min Range: -4.8220

Max Act: 4.3269. Min Act: -0.1700

Data Index: 470205 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 4.8220. Min Range: -4.8220

Max Act: 4.3030. Min Act: -0.1700

Data Index: 774369 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 4.8220. Min Range: -4.8220

Max Act: 4.2859. Min Act: -0.1700

Data Index: 1275961 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 4.8220. Min Range: -4.8220

Max Act: 4.2394. Min Act: -0.1700

Data Index: 1032720 (C4 (Web Text))

Max Activating Token Index: 781