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

Dataset: Open Web Text

Neuron 2017 in Layer 1

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: 4.6518. Min Range: -4.6518

Max Act: 4.6518. Min Act: -0.1700

Data Index: 3355059 (Open Web Text)

Max Activating Token Index: 526

Text #1

Max Range: 4.6518. Min Range: -4.6518

Max Act: 4.6180. Min Act: -0.1700

Data Index: 6908808 (Open Web Text)

Max Activating Token Index: 136

Text #2

Max Range: 4.6518. Min Range: -4.6518

Max Act: 4.6135. Min Act: -0.1700

Data Index: 5935705 (Open Web Text)

Max Activating Token Index: 498

Text #3

Max Range: 4.6518. Min Range: -4.6518

Max Act: 4.5919. Min Act: -0.1700

Data Index: 909565 (Open Web Text)

Max Activating Token Index: 622

Text #4

Max Range: 4.6518. Min Range: -4.6518

Max Act: 4.6071. Min Act: -0.1700

Data Index: 5849335 (Open Web Text)

Max Activating Token Index: 536

Text #5

Max Range: 4.6518. Min Range: -4.6518

Max Act: 4.6008. Min Act: -0.1700

Data Index: 4783705 (Open Web Text)

Max Activating Token Index: 456

Text #6

Max Range: 4.6518. Min Range: -4.6518

Max Act: 4.5939. Min Act: -0.1700

Data Index: 8431771 (Open Web Text)

Max Activating Token Index: 561

Text #7

Max Range: 4.6518. Min Range: -4.6518

Max Act: 4.6192. Min Act: -0.1700

Data Index: 3996487 (Open Web Text)

Max Activating Token Index: 939

Text #8

Max Range: 4.6518. Min Range: -4.6518

Max Act: 4.6031. Min Act: -0.1700

Data Index: 6693301 (Open Web Text)

Max Activating Token Index: 552

Text #9

Max Range: 4.6518. Min Range: -4.6518

Max Act: 4.5873. Min Act: -0.1700

Data Index: 2132605 (Open Web Text)

Max Activating Token Index: 687

Text #10

Max Range: 4.6518. Min Range: -4.6518

Max Act: 4.5513. Min Act: -0.1700

Data Index: 8795449 (Open Web Text)

Max Activating Token Index: 132

Text #11

Max Range: 4.6518. Min Range: -4.6518

Max Act: 4.5782. Min Act: -0.1700

Data Index: 5952537 (Open Web Text)

Max Activating Token Index: 519

Text #12

Max Range: 4.6518. Min Range: -4.6518

Max Act: 4.5656. Min Act: -0.1700

Data Index: 513305 (Open Web Text)

Max Activating Token Index: 612

Text #13

Max Range: 4.6518. Min Range: -4.6518

Max Act: 4.5602. Min Act: -0.1700

Data Index: 3362566 (Open Web Text)

Max Activating Token Index: 549

Text #14

Max Range: 4.6518. Min Range: -4.6518

Max Act: 4.5223. Min Act: -0.1700

Data Index: 1140795 (Open Web Text)

Max Activating Token Index: 151

Text #15

Max Range: 4.6518. Min Range: -4.6518

Max Act: 4.5398. Min Act: -0.1700

Data Index: 3269154 (Open Web Text)

Max Activating Token Index: 401

Text #16

Max Range: 4.6518. Min Range: -4.6518

Max Act: 4.5261. Min Act: -0.1700

Data Index: 4793771 (Open Web Text)

Max Activating Token Index: 716

Text #17

Max Range: 4.6518. Min Range: -4.6518

Max Act: 4.5398. Min Act: -0.1700

Data Index: 5026796 (Open Web Text)

Max Activating Token Index: 612

Text #18

Max Range: 4.6518. Min Range: -4.6518

Max Act: 4.5482. Min Act: -0.1700

Data Index: 447430 (Open Web Text)

Max Activating Token Index: 206

Text #19

Max Range: 4.6518. Min Range: -4.6518

Max Act: 4.5413. Min Act: -0.1700

Data Index: 967994 (Open Web Text)

Max Activating Token Index: 529