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

Dataset: Open Web Text

Neuron 2825 in Layer 6

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: 4.6833. Min Range: -4.6833

Max Act: 4.6833. Min Act: -0.1700

Data Index: 7445517 (Open Web Text)

Max Activating Token Index: 532

Text #1

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.4954. Min Act: -0.1700

Data Index: 7157431 (Open Web Text)

Max Activating Token Index: 435

Text #2

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.5049. Min Act: -0.1700

Data Index: 6976218 (Open Web Text)

Max Activating Token Index: 940

Text #3

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.5095. Min Act: -0.1700

Data Index: 1570284 (Open Web Text)

Max Activating Token Index: 555

Text #4

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.5108. Min Act: -0.1700

Data Index: 4312962 (Open Web Text)

Max Activating Token Index: 523

Text #5

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.4729. Min Act: -0.1700

Data Index: 2367247 (Open Web Text)

Max Activating Token Index: 313

Text #6

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.4583. Min Act: -0.1700

Data Index: 6728747 (Open Web Text)

Max Activating Token Index: 789

Text #7

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.4616. Min Act: -0.1700

Data Index: 3869796 (Open Web Text)

Max Activating Token Index: 236

Text #8

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.4079. Min Act: -0.1700

Data Index: 1506844 (Open Web Text)

Max Activating Token Index: 940

Text #9

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.3712. Min Act: -0.1700

Data Index: 2046972 (Open Web Text)

Max Activating Token Index: 604

Text #10

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.3582. Min Act: -0.1700

Data Index: 3924687 (Open Web Text)

Max Activating Token Index: 804

Text #11

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.3704. Min Act: -0.1700

Data Index: 6661096 (Open Web Text)

Max Activating Token Index: 553

Text #12

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.3829. Min Act: -0.1700

Data Index: 8424360 (Open Web Text)

Max Activating Token Index: 116

Text #13

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.3458. Min Act: -0.1700

Data Index: 3923719 (Open Web Text)

Max Activating Token Index: 84

Text #14

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.3356. Min Act: -0.1700

Data Index: 3370675 (Open Web Text)

Max Activating Token Index: 252

Text #15

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.3440. Min Act: -0.1700

Data Index: 225827 (Open Web Text)

Max Activating Token Index: 822

Text #16

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.3904. Min Act: -0.1700

Data Index: 6270142 (Open Web Text)

Max Activating Token Index: 393

Text #17

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.3041. Min Act: -0.1700

Data Index: 470366 (Open Web Text)

Max Activating Token Index: 957

Text #18

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.3413. Min Act: -0.1700

Data Index: 6728618 (Open Web Text)

Max Activating Token Index: 705

Text #19

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.2935. Min Act: -0.1700

Data Index: 2475057 (Open Web Text)

Max Activating Token Index: 499