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

Dataset: Open Web Text

Neuron 491 in Layer 0

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: 3.0780. Min Range: -3.0780

Max Act: 3.0780. Min Act: -0.1700

Data Index: 729669 (Open Web Text)

Max Activating Token Index: 302

Text #1

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9941. Min Act: -0.1700

Data Index: 5851304 (Open Web Text)

Max Activating Token Index: 502

Text #2

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9566. Min Act: -0.1700

Data Index: 1370644 (Open Web Text)

Max Activating Token Index: 866

Text #3

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9585. Min Act: -0.1700

Data Index: 4851132 (Open Web Text)

Max Activating Token Index: 39

Text #4

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9374. Min Act: -0.1700

Data Index: 3407475 (Open Web Text)

Max Activating Token Index: 378

Text #5

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9319. Min Act: -0.1700

Data Index: 3884270 (Open Web Text)

Max Activating Token Index: 29

Text #6

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9404. Min Act: -0.1700

Data Index: 4832140 (Open Web Text)

Max Activating Token Index: 252

Text #7

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9440. Min Act: -0.1700

Data Index: 6053307 (Open Web Text)

Max Activating Token Index: 950

Text #8

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9321. Min Act: -0.1700

Data Index: 3207214 (Open Web Text)

Max Activating Token Index: 35

Text #9

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9244. Min Act: -0.1700

Data Index: 655407 (Open Web Text)

Max Activating Token Index: 965

Text #10

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9221. Min Act: -0.1700

Data Index: 8802378 (Open Web Text)

Max Activating Token Index: 376

Text #11

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9289. Min Act: -0.1700

Data Index: 1100721 (Open Web Text)

Max Activating Token Index: 875

Text #12

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9045. Min Act: -0.1700

Data Index: 1707033 (Open Web Text)

Max Activating Token Index: 147

Text #13

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9133. Min Act: -0.1700

Data Index: 8497278 (Open Web Text)

Max Activating Token Index: 631

Text #14

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9091. Min Act: -0.1700

Data Index: 8497279 (Open Web Text)

Max Activating Token Index: 511

Text #15

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9154. Min Act: -0.1700

Data Index: 5015651 (Open Web Text)

Max Activating Token Index: 944

Text #16

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9058. Min Act: -0.1700

Data Index: 5829040 (Open Web Text)

Max Activating Token Index: 104

Text #17

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.8911. Min Act: -0.1700

Data Index: 140166 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.8844. Min Act: -0.1700

Data Index: 4191782 (Open Web Text)

Max Activating Token Index: 67

Text #19

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.8870. Min Act: -0.1700

Data Index: 4832124 (Open Web Text)

Max Activating Token Index: 173