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

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

Neuron 1800 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: 3.7401. Min Range: -3.7401

Max Act: 3.7401. Min Act: -0.1700

Data Index: 137679 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 3.7401. Min Range: -3.7401

Max Act: 3.7276. Min Act: -0.1700

Data Index: 799466 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 3.7401. Min Range: -3.7401

Max Act: 3.7070. Min Act: -0.1700

Data Index: 1013964 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 3.7401. Min Range: -3.7401

Max Act: 3.6964. Min Act: -0.1700

Data Index: 805193 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 3.7401. Min Range: -3.7401

Max Act: 3.6807. Min Act: -0.1700

Data Index: 701729 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 3.7401. Min Range: -3.7401

Max Act: 3.6455. Min Act: -0.1700

Data Index: 39170 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 3.7401. Min Range: -3.7401

Max Act: 3.6450. Min Act: -0.1700

Data Index: 470082 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 3.7401. Min Range: -3.7401

Max Act: 3.6527. Min Act: -0.1700

Data Index: 1070062 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 3.7401. Min Range: -3.7401

Max Act: 3.6335. Min Act: -0.1700

Data Index: 32410 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 3.7401. Min Range: -3.7401

Max Act: 3.6072. Min Act: -0.1700

Data Index: 1022891 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 3.7401. Min Range: -3.7401

Max Act: 3.6166. Min Act: -0.1699

Data Index: 659259 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 3.7401. Min Range: -3.7401

Max Act: 3.6032. Min Act: -0.1700

Data Index: 587331 (C4 (Web Text))

Max Activating Token Index: 583

Text #12

Max Range: 3.7401. Min Range: -3.7401

Max Act: 3.6027. Min Act: -0.1700

Data Index: 446066 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 3.7401. Min Range: -3.7401

Max Act: 3.5810. Min Act: -0.1700

Data Index: 1023447 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 3.7401. Min Range: -3.7401

Max Act: 3.5813. Min Act: -0.1700

Data Index: 717205 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 3.7401. Min Range: -3.7401

Max Act: 3.5790. Min Act: -0.1700

Data Index: 1216301 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 3.7401. Min Range: -3.7401

Max Act: 3.5729. Min Act: -0.1700

Data Index: 423959 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 3.7401. Min Range: -3.7401

Max Act: 3.5617. Min Act: -0.1700

Data Index: 79441 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 3.7401. Min Range: -3.7401

Max Act: 3.5408. Min Act: -0.1699

Data Index: 976364 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 3.7401. Min Range: -3.7401

Max Act: 3.5490. Min Act: -0.1700

Data Index: 704229 (C4 (Web Text))

Max Activating Token Index: 54