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

Dataset: Open Web Text

Neuron 128 in Layer 2

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: 4.0726. Min Range: -4.0726

Max Act: 4.0726. Min Act: -0.1700

Data Index: 8243319 (Open Web Text)

Max Activating Token Index: 153

Text #1

Max Range: 4.0726. Min Range: -4.0726

Max Act: 3.9566. Min Act: -0.1700

Data Index: 8312056 (Open Web Text)

Max Activating Token Index: 244

Text #2

Max Range: 4.0726. Min Range: -4.0726

Max Act: 3.8986. Min Act: -0.1700

Data Index: 2742026 (Open Web Text)

Max Activating Token Index: 825

Text #3

Max Range: 4.0726. Min Range: -4.0726

Max Act: 3.9340. Min Act: -0.1700

Data Index: 2203405 (Open Web Text)

Max Activating Token Index: 401

Text #4

Max Range: 4.0726. Min Range: -4.0726

Max Act: 3.9389. Min Act: -0.1700

Data Index: 6920768 (Open Web Text)

Max Activating Token Index: 804

Text #5

Max Range: 4.0726. Min Range: -4.0726

Max Act: 3.9114. Min Act: -0.1700

Data Index: 5358134 (Open Web Text)

Max Activating Token Index: 910

Text #6

Max Range: 4.0726. Min Range: -4.0726

Max Act: 3.9206. Min Act: -0.1700

Data Index: 2647165 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 4.0726. Min Range: -4.0726

Max Act: 3.8879. Min Act: -0.1700

Data Index: 2210297 (Open Web Text)

Max Activating Token Index: 953

Text #8

Max Range: 4.0726. Min Range: -4.0726

Max Act: 3.8738. Min Act: -0.1700

Data Index: 5513255 (Open Web Text)

Max Activating Token Index: 393

Text #9

Max Range: 4.0726. Min Range: -4.0726

Max Act: 3.8895. Min Act: -0.1700

Data Index: 6685253 (Open Web Text)

Max Activating Token Index: 333

Text #10

Max Range: 4.0726. Min Range: -4.0726

Max Act: 3.8408. Min Act: -0.1699

Data Index: 4243885 (Open Web Text)

Max Activating Token Index: 156

Text #11

Max Range: 4.0726. Min Range: -4.0726

Max Act: 3.8599. Min Act: -0.1700

Data Index: 5541931 (Open Web Text)

Max Activating Token Index: 56

Text #12

Max Range: 4.0726. Min Range: -4.0726

Max Act: 3.8944. Min Act: -0.1700

Data Index: 7250269 (Open Web Text)

Max Activating Token Index: 568

Text #13

Max Range: 4.0726. Min Range: -4.0726

Max Act: 3.8847. Min Act: -0.1700

Data Index: 7241191 (Open Web Text)

Max Activating Token Index: 32

Text #14

Max Range: 4.0726. Min Range: -4.0726

Max Act: 3.8449. Min Act: -0.1700

Data Index: 5225842 (Open Web Text)

Max Activating Token Index: 533

Text #15

Max Range: 4.0726. Min Range: -4.0726

Max Act: 3.8844. Min Act: -0.1700

Data Index: 6311416 (Open Web Text)

Max Activating Token Index: 32

Text #16

Max Range: 4.0726. Min Range: -4.0726

Max Act: 3.8787. Min Act: -0.1700

Data Index: 3816296 (Open Web Text)

Max Activating Token Index: 158

Text #17

Max Range: 4.0726. Min Range: -4.0726

Max Act: 3.8479. Min Act: -0.1700

Data Index: 6463270 (Open Web Text)

Max Activating Token Index: 232

Text #18

Max Range: 4.0726. Min Range: -4.0726

Max Act: 3.8480. Min Act: -0.1700

Data Index: 2818394 (Open Web Text)

Max Activating Token Index: 802

Text #19

Max Range: 4.0726. Min Range: -4.0726

Max Act: 3.8466. Min Act: -0.1700

Data Index: 6326279 (Open Web Text)

Max Activating Token Index: 314