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

Dataset: Open Web Text

Neuron 1252 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: 5.5016. Min Range: -5.5016

Max Act: 5.5016. Min Act: -0.1700

Data Index: 1823940 (Open Web Text)

Max Activating Token Index: 343

Text #1

Max Range: 5.5016. Min Range: -5.5016

Max Act: 4.9154. Min Act: -0.1700

Data Index: 4111488 (Open Web Text)

Max Activating Token Index: 343

Text #2

Max Range: 5.5016. Min Range: -5.5016

Max Act: 4.8612. Min Act: -0.1700

Data Index: 5142883 (Open Web Text)

Max Activating Token Index: 253

Text #3

Max Range: 5.5016. Min Range: -5.5016

Max Act: 4.8897. Min Act: -0.1700

Data Index: 556079 (Open Web Text)

Max Activating Token Index: 40

Text #4

Max Range: 5.5016. Min Range: -5.5016

Max Act: 4.8720. Min Act: -0.1700

Data Index: 3467295 (Open Web Text)

Max Activating Token Index: 48

Text #5

Max Range: 5.5016. Min Range: -5.5016

Max Act: 4.8461. Min Act: -0.1700

Data Index: 6325034 (Open Web Text)

Max Activating Token Index: 659

Text #6

Max Range: 5.5016. Min Range: -5.5016

Max Act: 4.8424. Min Act: -0.1700

Data Index: 4560532 (Open Web Text)

Max Activating Token Index: 921

Text #7

Max Range: 5.5016. Min Range: -5.5016

Max Act: 4.8218. Min Act: -0.1700

Data Index: 7869266 (Open Web Text)

Max Activating Token Index: 945

Text #8

Max Range: 5.5016. Min Range: -5.5016

Max Act: 4.7953. Min Act: -0.1700

Data Index: 8313292 (Open Web Text)

Max Activating Token Index: 233

Text #9

Max Range: 5.5016. Min Range: -5.5016

Max Act: 4.7975. Min Act: -0.1700

Data Index: 6061462 (Open Web Text)

Max Activating Token Index: 362

Text #10

Max Range: 5.5016. Min Range: -5.5016

Max Act: 4.7656. Min Act: -0.1700

Data Index: 2755233 (Open Web Text)

Max Activating Token Index: 661

Text #11

Max Range: 5.5016. Min Range: -5.5016

Max Act: 4.7484. Min Act: -0.1700

Data Index: 5946133 (Open Web Text)

Max Activating Token Index: 226

Text #12

Max Range: 5.5016. Min Range: -5.5016

Max Act: 4.7576. Min Act: -0.1700

Data Index: 640914 (Open Web Text)

Max Activating Token Index: 758

Text #13

Max Range: 5.5016. Min Range: -5.5016

Max Act: 4.6999. Min Act: -0.1700

Data Index: 1543421 (Open Web Text)

Max Activating Token Index: 1020

Text #14

Max Range: 5.5016. Min Range: -5.5016

Max Act: 4.7327. Min Act: -0.1700

Data Index: 7208486 (Open Web Text)

Max Activating Token Index: 770

Text #15

Max Range: 5.5016. Min Range: -5.5016

Max Act: 4.7611. Min Act: -0.1700

Data Index: 7482104 (Open Web Text)

Max Activating Token Index: 717

Text #16

Max Range: 5.5016. Min Range: -5.5016

Max Act: 4.7460. Min Act: -0.1700

Data Index: 6532188 (Open Web Text)

Max Activating Token Index: 472

Text #17

Max Range: 5.5016. Min Range: -5.5016

Max Act: 4.7614. Min Act: -0.1700

Data Index: 3497376 (Open Web Text)

Max Activating Token Index: 578

Text #18

Max Range: 5.5016. Min Range: -5.5016

Max Act: 4.7439. Min Act: -0.1700

Data Index: 219372 (Open Web Text)

Max Activating Token Index: 367

Text #19

Max Range: 5.5016. Min Range: -5.5016

Max Act: 4.6888. Min Act: -0.1700

Data Index: 7928471 (Open Web Text)

Max Activating Token Index: 590