Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2375 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 1.2794. Min Range: -1.2794

Max Act: 1.2612. Min Act: -0.1700

Data Index: 7875173 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.2794. Min Range: -1.2794

Max Act: 1.2794. Min Act: -0.1700

Data Index: 284403 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 1.2794. Min Range: -1.2794

Max Act: 1.2787. Min Act: -0.1700

Data Index: 7173055 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 1.2794. Min Range: -1.2794

Max Act: 1.2576. Min Act: -0.1700

Data Index: 6996026 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.2794. Min Range: -1.2794

Max Act: 1.2413. Min Act: -0.1700

Data Index: 5497307 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 1.2794. Min Range: -1.2794

Max Act: 1.1962. Min Act: -0.1700

Data Index: 6204601 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 1.2794. Min Range: -1.2794

Max Act: 1.1824. Min Act: -0.1700

Data Index: 3235491 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 1.2794. Min Range: -1.2794

Max Act: 1.2524. Min Act: -0.1700

Data Index: 5046510 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 1.2794. Min Range: -1.2794

Max Act: 1.1740. Min Act: -0.1700

Data Index: 575939 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 1.2794. Min Range: -1.2794

Max Act: 1.1446. Min Act: -0.1700

Data Index: 1414914 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 1.2794. Min Range: -1.2794

Max Act: 1.1137. Min Act: -0.1700

Data Index: 940826 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 1.2794. Min Range: -1.2794

Max Act: 1.1631. Min Act: -0.1700

Data Index: 688258 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 1.2794. Min Range: -1.2794

Max Act: 1.1554. Min Act: -0.1700

Data Index: 7755296 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 1.2794. Min Range: -1.2794

Max Act: 1.1435. Min Act: -0.1700

Data Index: 3996230 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 1.2794. Min Range: -1.2794

Max Act: 1.1483. Min Act: -0.1700

Data Index: 2333144 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 1.2794. Min Range: -1.2794

Max Act: 1.1173. Min Act: -0.1700

Data Index: 3742383 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 1.2794. Min Range: -1.2794

Max Act: 1.1253. Min Act: -0.1700

Data Index: 7276696 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 1.2794. Min Range: -1.2794

Max Act: 1.1056. Min Act: -0.1700

Data Index: 8154366 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 1.2794. Min Range: -1.2794

Max Act: 1.1150. Min Act: -0.1700

Data Index: 8463884 (Open Web Text)

Max Activating Token Index: 725

Text #19

Max Range: 1.2794. Min Range: -1.2794

Max Act: 1.1342. Min Act: -0.1700

Data Index: 4091164 (Open Web Text)

Max Activating Token Index: 1023