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

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

Neuron 1117 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: 3.0790. Min Range: -3.0790

Max Act: 3.0790. Min Act: -0.1700

Data Index: 657350 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 3.0790. Min Range: -3.0790

Max Act: 3.0529. Min Act: -0.1700

Data Index: 74655 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 3.0790. Min Range: -3.0790

Max Act: 3.0380. Min Act: -0.1700

Data Index: 416712 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 3.0790. Min Range: -3.0790

Max Act: 2.9982. Min Act: -0.1700

Data Index: 612426 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 3.0790. Min Range: -3.0790

Max Act: 2.9895. Min Act: -0.1700

Data Index: 1042430 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 3.0790. Min Range: -3.0790

Max Act: 2.9807. Min Act: -0.1700

Data Index: 394171 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 3.0790. Min Range: -3.0790

Max Act: 2.9998. Min Act: -0.1700

Data Index: 368978 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 3.0790. Min Range: -3.0790

Max Act: 3.0055. Min Act: -0.1700

Data Index: 1140782 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 3.0790. Min Range: -3.0790

Max Act: 2.9541. Min Act: -0.1698

Data Index: 578782 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 3.0790. Min Range: -3.0790

Max Act: 2.9528. Min Act: -0.1700

Data Index: 838643 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 3.0790. Min Range: -3.0790

Max Act: 2.9485. Min Act: -0.1700

Data Index: 230660 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 3.0790. Min Range: -3.0790

Max Act: 2.9555. Min Act: -0.1700

Data Index: 747693 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 3.0790. Min Range: -3.0790

Max Act: 2.9620. Min Act: -0.1699

Data Index: 562627 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 3.0790. Min Range: -3.0790

Max Act: 2.9676. Min Act: -0.1700

Data Index: 184487 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 3.0790. Min Range: -3.0790

Max Act: 2.9169. Min Act: -0.1700

Data Index: 623722 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 3.0790. Min Range: -3.0790

Max Act: 2.9133. Min Act: -0.1700

Data Index: 505358 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 3.0790. Min Range: -3.0790

Max Act: 2.9192. Min Act: -0.1700

Data Index: 739978 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 3.0790. Min Range: -3.0790

Max Act: 2.9444. Min Act: -0.1697

Data Index: 392574 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 3.0790. Min Range: -3.0790

Max Act: 2.9188. Min Act: -0.1700

Data Index: 604810 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 3.0790. Min Range: -3.0790

Max Act: 2.9311. Min Act: -0.1700

Data Index: 13065 (C4 (Web Text))

Max Activating Token Index: 75