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

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

Neuron 1738 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: 3.6747. Min Range: -3.6747

Max Act: 3.6747. Min Act: -0.1700

Data Index: 415863 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.5663. Min Act: -0.1700

Data Index: 138050 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.5645. Min Act: -0.1700

Data Index: 839707 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.5491. Min Act: -0.1700

Data Index: 973883 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.5300. Min Act: -0.1700

Data Index: 1386838 (Python Code)

Max Activating Token Index: 701

Text #5

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.5631. Min Act: -0.1700

Data Index: 958176 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.5451. Min Act: -0.1700

Data Index: 966598 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.5285. Min Act: -0.1700

Data Index: 1190773 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.5106. Min Act: -0.1700

Data Index: 1599151 (Python Code)

Max Activating Token Index: 96

Text #9

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.4962. Min Act: -0.1700

Data Index: 126277 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.5022. Min Act: -0.1700

Data Index: 1325090 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.4844. Min Act: -0.1700

Data Index: 1269758 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.4926. Min Act: -0.1700

Data Index: 126265 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.4963. Min Act: -0.1700

Data Index: 953844 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.4831. Min Act: -0.1700

Data Index: 1139027 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.4796. Min Act: -0.1700

Data Index: 954596 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.4775. Min Act: -0.1700

Data Index: 67041 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.4721. Min Act: -0.1700

Data Index: 754067 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.4767. Min Act: -0.1700

Data Index: 1573564 (Python Code)

Max Activating Token Index: 734

Text #19

Max Range: 3.6747. Min Range: -3.6747

Max Act: 3.4501. Min Act: -0.1700

Data Index: 97266 (C4 (Web Text))

Max Activating Token Index: 253