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

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

Neuron 870 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: 3.7693. Min Range: -3.7693

Max Act: 3.7693. Min Act: -0.1700

Data Index: 672011 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 3.7693. Min Range: -3.7693

Max Act: 3.6625. Min Act: -0.1700

Data Index: 652730 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 3.7693. Min Range: -3.7693

Max Act: 3.6601. Min Act: -0.1699

Data Index: 74229 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 3.7693. Min Range: -3.7693

Max Act: 3.6599. Min Act: -0.1700

Data Index: 1230497 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 3.7693. Min Range: -3.7693

Max Act: 3.6181. Min Act: -0.1700

Data Index: 394209 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 3.7693. Min Range: -3.7693

Max Act: 3.5630. Min Act: -0.1700

Data Index: 563253 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 3.7693. Min Range: -3.7693

Max Act: 3.5510. Min Act: -0.1700

Data Index: 1092842 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 3.7693. Min Range: -3.7693

Max Act: 3.5716. Min Act: -0.1699

Data Index: 895827 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 3.7693. Min Range: -3.7693

Max Act: 3.5771. Min Act: -0.1700

Data Index: 191452 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 3.7693. Min Range: -3.7693

Max Act: 3.5588. Min Act: -0.1700

Data Index: 1089047 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 3.7693. Min Range: -3.7693

Max Act: 3.5532. Min Act: -0.1700

Data Index: 267777 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 3.7693. Min Range: -3.7693

Max Act: 3.5435. Min Act: -0.1700

Data Index: 292991 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 3.7693. Min Range: -3.7693

Max Act: 3.5535. Min Act: -0.1700

Data Index: 402771 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 3.7693. Min Range: -3.7693

Max Act: 3.5377. Min Act: -0.1700

Data Index: 1029142 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 3.7693. Min Range: -3.7693

Max Act: 3.5369. Min Act: -0.1699

Data Index: 761289 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 3.7693. Min Range: -3.7693

Max Act: 3.5426. Min Act: -0.1700

Data Index: 1015933 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 3.7693. Min Range: -3.7693

Max Act: 3.5396. Min Act: -0.1700

Data Index: 927228 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 3.7693. Min Range: -3.7693

Max Act: 3.5336. Min Act: -0.1699

Data Index: 123256 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 3.7693. Min Range: -3.7693

Max Act: 3.5480. Min Act: -0.1700

Data Index: 496480 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 3.7693. Min Range: -3.7693

Max Act: 3.5220. Min Act: -0.1700

Data Index: 566229 (C4 (Web Text))

Max Activating Token Index: 30