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

Dataset: Open Web Text

Neuron 2140 in Layer 2

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: 3.7627. Min Range: -3.7627

Max Act: 3.7604. Min Act: -0.1700

Data Index: 3163818 (Open Web Text)

Max Activating Token Index: 408

Text #1

Max Range: 3.7627. Min Range: -3.7627

Max Act: 3.7627. Min Act: -0.1700

Data Index: 2711638 (Open Web Text)

Max Activating Token Index: 33

Text #2

Max Range: 3.7627. Min Range: -3.7627

Max Act: 3.7320. Min Act: -0.1700

Data Index: 7615404 (Open Web Text)

Max Activating Token Index: 637

Text #3

Max Range: 3.7627. Min Range: -3.7627

Max Act: 3.7130. Min Act: -0.1700

Data Index: 7224180 (Open Web Text)

Max Activating Token Index: 26

Text #4

Max Range: 3.7627. Min Range: -3.7627

Max Act: 3.7483. Min Act: -0.1700

Data Index: 189946 (Open Web Text)

Max Activating Token Index: 221

Text #5

Max Range: 3.7627. Min Range: -3.7627

Max Act: 3.7186. Min Act: -0.1700

Data Index: 7908259 (Open Web Text)

Max Activating Token Index: 33

Text #6

Max Range: 3.7627. Min Range: -3.7627

Max Act: 3.6969. Min Act: -0.1700

Data Index: 693054 (Open Web Text)

Max Activating Token Index: 98

Text #7

Max Range: 3.7627. Min Range: -3.7627

Max Act: 3.6951. Min Act: -0.1700

Data Index: 5418977 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 3.7627. Min Range: -3.7627

Max Act: 3.6840. Min Act: -0.1700

Data Index: 7693154 (Open Web Text)

Max Activating Token Index: 295

Text #9

Max Range: 3.7627. Min Range: -3.7627

Max Act: 3.6851. Min Act: -0.1700

Data Index: 5079873 (Open Web Text)

Max Activating Token Index: 21

Text #10

Max Range: 3.7627. Min Range: -3.7627

Max Act: 3.6787. Min Act: -0.1700

Data Index: 189949 (Open Web Text)

Max Activating Token Index: 149

Text #11

Max Range: 3.7627. Min Range: -3.7627

Max Act: 3.6872. Min Act: -0.1700

Data Index: 8627647 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.7627. Min Range: -3.7627

Max Act: 3.6535. Min Act: -0.1700

Data Index: 6296665 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 3.7627. Min Range: -3.7627

Max Act: 3.6632. Min Act: -0.1700

Data Index: 6922196 (Open Web Text)

Max Activating Token Index: 18

Text #14

Max Range: 3.7627. Min Range: -3.7627

Max Act: 3.6506. Min Act: -0.1700

Data Index: 7097338 (Open Web Text)

Max Activating Token Index: 502

Text #15

Max Range: 3.7627. Min Range: -3.7627

Max Act: 3.6511. Min Act: -0.1700

Data Index: 189971 (Open Web Text)

Max Activating Token Index: 545

Text #16

Max Range: 3.7627. Min Range: -3.7627

Max Act: 3.6667. Min Act: -0.1700

Data Index: 8200863 (Open Web Text)

Max Activating Token Index: 17

Text #17

Max Range: 3.7627. Min Range: -3.7627

Max Act: 3.6456. Min Act: -0.1700

Data Index: 8392569 (Open Web Text)

Max Activating Token Index: 901

Text #18

Max Range: 3.7627. Min Range: -3.7627

Max Act: 3.6644. Min Act: -0.1700

Data Index: 189966 (Open Web Text)

Max Activating Token Index: 114

Text #19

Max Range: 3.7627. Min Range: -3.7627

Max Act: 3.6498. Min Act: -0.1700

Data Index: 7246477 (Open Web Text)

Max Activating Token Index: 145