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

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

Neuron 327 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: 5.8002. Min Range: -5.8002

Max Act: 5.8002. Min Act: -0.1700

Data Index: 248169 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 5.8002. Min Range: -5.8002

Max Act: 5.7311. Min Act: -0.1700

Data Index: 1089948 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 5.8002. Min Range: -5.8002

Max Act: 5.6489. Min Act: -0.1700

Data Index: 1008446 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 5.8002. Min Range: -5.8002

Max Act: 5.5662. Min Act: -0.1700

Data Index: 360371 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 5.8002. Min Range: -5.8002

Max Act: 5.5490. Min Act: -0.1700

Data Index: 647223 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 5.8002. Min Range: -5.8002

Max Act: 5.5420. Min Act: -0.1700

Data Index: 948330 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 5.8002. Min Range: -5.8002

Max Act: 5.4566. Min Act: -0.1700

Data Index: 875686 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 5.8002. Min Range: -5.8002

Max Act: 5.4557. Min Act: -0.1700

Data Index: 912688 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 5.8002. Min Range: -5.8002

Max Act: 5.4014. Min Act: -0.1700

Data Index: 865869 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 5.8002. Min Range: -5.8002

Max Act: 5.4464. Min Act: -0.1700

Data Index: 183146 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 5.8002. Min Range: -5.8002

Max Act: 5.4054. Min Act: -0.1700

Data Index: 1264556 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 5.8002. Min Range: -5.8002

Max Act: 5.4156. Min Act: -0.1700

Data Index: 363277 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 5.8002. Min Range: -5.8002

Max Act: 5.3862. Min Act: -0.1700

Data Index: 575775 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 5.8002. Min Range: -5.8002

Max Act: 5.3291. Min Act: -0.1700

Data Index: 988942 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 5.8002. Min Range: -5.8002

Max Act: 5.3191. Min Act: -0.1700

Data Index: 1560558 (Python Code)

Max Activating Token Index: 333

Text #15

Max Range: 5.8002. Min Range: -5.8002

Max Act: 5.3076. Min Act: -0.1700

Data Index: 1171039 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 5.8002. Min Range: -5.8002

Max Act: 5.3437. Min Act: -0.1700

Data Index: 1311747 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 5.8002. Min Range: -5.8002

Max Act: 5.3294. Min Act: -0.1700

Data Index: 22722 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 5.8002. Min Range: -5.8002

Max Act: 5.2621. Min Act: -0.1700

Data Index: 1303713 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 5.8002. Min Range: -5.8002

Max Act: 5.2660. Min Act: -0.1700

Data Index: 487938 (C4 (Web Text))

Max Activating Token Index: 205