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

Dataset: Open Web Text

Neuron 2264 in Layer 5

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: 3.6857. Min Range: -3.6857

Max Act: 3.6857. Min Act: -0.1700

Data Index: 6901185 (Open Web Text)

Max Activating Token Index: 72

Text #1

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.6074. Min Act: -0.1700

Data Index: 8553932 (Open Web Text)

Max Activating Token Index: 604

Text #2

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.5622. Min Act: -0.1700

Data Index: 7371418 (Open Web Text)

Max Activating Token Index: 938

Text #3

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.5592. Min Act: -0.1700

Data Index: 7244180 (Open Web Text)

Max Activating Token Index: 709

Text #4

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.5887. Min Act: -0.1700

Data Index: 3381657 (Open Web Text)

Max Activating Token Index: 452

Text #5

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.5526. Min Act: -0.1700

Data Index: 2848587 (Open Web Text)

Max Activating Token Index: 75

Text #6

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.5324. Min Act: -0.1700

Data Index: 3915697 (Open Web Text)

Max Activating Token Index: 101

Text #7

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.5301. Min Act: -0.1700

Data Index: 7384624 (Open Web Text)

Max Activating Token Index: 840

Text #8

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.4898. Min Act: -0.1700

Data Index: 335204 (Open Web Text)

Max Activating Token Index: 801

Text #9

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.5108. Min Act: -0.1700

Data Index: 3514300 (Open Web Text)

Max Activating Token Index: 140

Text #10

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.4836. Min Act: -0.1700

Data Index: 2678569 (Open Web Text)

Max Activating Token Index: 842

Text #11

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.4676. Min Act: -0.1700

Data Index: 3409162 (Open Web Text)

Max Activating Token Index: 816

Text #12

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.4660. Min Act: -0.1700

Data Index: 1397481 (Open Web Text)

Max Activating Token Index: 513

Text #13

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.4825. Min Act: -0.1700

Data Index: 6896453 (Open Web Text)

Max Activating Token Index: 902

Text #14

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.4737. Min Act: -0.1700

Data Index: 6261667 (Open Web Text)

Max Activating Token Index: 25

Text #15

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.4961. Min Act: -0.1700

Data Index: 1142137 (Open Web Text)

Max Activating Token Index: 434

Text #16

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.4704. Min Act: -0.1700

Data Index: 2192618 (Open Web Text)

Max Activating Token Index: 525

Text #17

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.4795. Min Act: -0.1700

Data Index: 1907750 (Open Web Text)

Max Activating Token Index: 919

Text #18

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.4455. Min Act: -0.1700

Data Index: 2682212 (Open Web Text)

Max Activating Token Index: 721

Text #19

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.4210. Min Act: -0.1700

Data Index: 2740457 (Open Web Text)

Max Activating Token Index: 596