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

Dataset: Open Web Text

Neuron 974 in Layer 3

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: 1.9872. Min Range: -1.9872

Max Act: 1.9872. Min Act: -0.1700

Data Index: 8448567 (Open Web Text)

Max Activating Token Index: 690

Text #1

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.9506. Min Act: -0.1700

Data Index: 3020030 (Open Web Text)

Max Activating Token Index: 158

Text #2

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.9366. Min Act: -0.1700

Data Index: 3551242 (Open Web Text)

Max Activating Token Index: 267

Text #3

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.8952. Min Act: -0.1700

Data Index: 4267866 (Open Web Text)

Max Activating Token Index: 652

Text #4

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.8992. Min Act: -0.1699

Data Index: 761625 (Open Web Text)

Max Activating Token Index: 383

Text #5

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.8775. Min Act: -0.1700

Data Index: 6751191 (Open Web Text)

Max Activating Token Index: 995

Text #6

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.8614. Min Act: -0.1700

Data Index: 2139425 (Open Web Text)

Max Activating Token Index: 318

Text #7

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.8796. Min Act: -0.1700

Data Index: 4792263 (Open Web Text)

Max Activating Token Index: 186

Text #8

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.8703. Min Act: -0.1700

Data Index: 3641382 (Open Web Text)

Max Activating Token Index: 268

Text #9

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.8466. Min Act: -0.1700

Data Index: 256619 (Open Web Text)

Max Activating Token Index: 1005

Text #10

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.8823. Min Act: -0.1700

Data Index: 3930143 (Open Web Text)

Max Activating Token Index: 408

Text #11

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.8713. Min Act: -0.1700

Data Index: 2519426 (Open Web Text)

Max Activating Token Index: 401

Text #12

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.8604. Min Act: -0.1700

Data Index: 7627450 (Open Web Text)

Max Activating Token Index: 303

Text #13

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.8720. Min Act: -0.1700

Data Index: 6345481 (Open Web Text)

Max Activating Token Index: 617

Text #14

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.8432. Min Act: -0.1700

Data Index: 3398767 (Open Web Text)

Max Activating Token Index: 72

Text #15

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.8577. Min Act: -0.1700

Data Index: 2283827 (Open Web Text)

Max Activating Token Index: 414

Text #16

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.8296. Min Act: -0.1700

Data Index: 2345952 (Open Web Text)

Max Activating Token Index: 700

Text #17

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.8530. Min Act: -0.1700

Data Index: 4703107 (Open Web Text)

Max Activating Token Index: 281

Text #18

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.8572. Min Act: -0.1700

Data Index: 2324036 (Open Web Text)

Max Activating Token Index: 904

Text #19

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.8359. Min Act: -0.1700

Data Index: 6666504 (Open Web Text)

Max Activating Token Index: 237