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

Dataset: Open Web Text

Neuron 2359 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: 5.6857. Min Range: -5.6857

Max Act: 5.6857. Min Act: -0.1700

Data Index: 99830 (Open Web Text)

Max Activating Token Index: 302

Text #1

Max Range: 5.6857. Min Range: -5.6857

Max Act: 5.6162. Min Act: -0.1700

Data Index: 882217 (Open Web Text)

Max Activating Token Index: 119

Text #2

Max Range: 5.6857. Min Range: -5.6857

Max Act: 5.4697. Min Act: -0.1700

Data Index: 3047905 (Open Web Text)

Max Activating Token Index: 877

Text #3

Max Range: 5.6857. Min Range: -5.6857

Max Act: 5.3666. Min Act: -0.1700

Data Index: 7369540 (Open Web Text)

Max Activating Token Index: 381

Text #4

Max Range: 5.6857. Min Range: -5.6857

Max Act: 5.3567. Min Act: -0.1700

Data Index: 8390293 (Open Web Text)

Max Activating Token Index: 465

Text #5

Max Range: 5.6857. Min Range: -5.6857

Max Act: 5.3447. Min Act: -0.1700

Data Index: 1326669 (Open Web Text)

Max Activating Token Index: 139

Text #6

Max Range: 5.6857. Min Range: -5.6857

Max Act: 5.3856. Min Act: -0.1700

Data Index: 8464744 (Open Web Text)

Max Activating Token Index: 1019

Text #7

Max Range: 5.6857. Min Range: -5.6857

Max Act: 5.3310. Min Act: -0.1700

Data Index: 6690754 (Open Web Text)

Max Activating Token Index: 58

Text #8

Max Range: 5.6857. Min Range: -5.6857

Max Act: 5.3731. Min Act: -0.1700

Data Index: 5176686 (Open Web Text)

Max Activating Token Index: 292

Text #9

Max Range: 5.6857. Min Range: -5.6857

Max Act: 5.3418. Min Act: -0.1700

Data Index: 5176687 (Open Web Text)

Max Activating Token Index: 36

Text #10

Max Range: 5.6857. Min Range: -5.6857

Max Act: 5.3319. Min Act: -0.1700

Data Index: 6516901 (Open Web Text)

Max Activating Token Index: 530

Text #11

Max Range: 5.6857. Min Range: -5.6857

Max Act: 5.2653. Min Act: -0.1700

Data Index: 4054774 (Open Web Text)

Max Activating Token Index: 771

Text #12

Max Range: 5.6857. Min Range: -5.6857

Max Act: 5.2523. Min Act: -0.1700

Data Index: 2614707 (Open Web Text)

Max Activating Token Index: 995

Text #13

Max Range: 5.6857. Min Range: -5.6857

Max Act: 5.2524. Min Act: -0.1700

Data Index: 193569 (Open Web Text)

Max Activating Token Index: 715

Text #14

Max Range: 5.6857. Min Range: -5.6857

Max Act: 5.2421. Min Act: -0.1700

Data Index: 5903251 (Open Web Text)

Max Activating Token Index: 11

Text #15

Max Range: 5.6857. Min Range: -5.6857

Max Act: 5.2296. Min Act: -0.1700

Data Index: 6907009 (Open Web Text)

Max Activating Token Index: 550

Text #16

Max Range: 5.6857. Min Range: -5.6857

Max Act: 5.2171. Min Act: -0.1700

Data Index: 2615529 (Open Web Text)

Max Activating Token Index: 436

Text #17

Max Range: 5.6857. Min Range: -5.6857

Max Act: 5.1744. Min Act: -0.1700

Data Index: 817820 (Open Web Text)

Max Activating Token Index: 1004

Text #18

Max Range: 5.6857. Min Range: -5.6857

Max Act: 5.1472. Min Act: -0.1700

Data Index: 7928995 (Open Web Text)

Max Activating Token Index: 254

Text #19

Max Range: 5.6857. Min Range: -5.6857

Max Act: 5.1494. Min Act: -0.1700

Data Index: 1130207 (Open Web Text)

Max Activating Token Index: 454