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

Dataset: Open Web Text

Neuron 624 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: 4.5804. Min Range: -4.5804

Max Act: 4.5398. Min Act: -0.1700

Data Index: 1416159 (Open Web Text)

Max Activating Token Index: 315

Text #1

Max Range: 4.5804. Min Range: -4.5804

Max Act: 4.5804. Min Act: -0.1700

Data Index: 8054044 (Open Web Text)

Max Activating Token Index: 630

Text #2

Max Range: 4.5804. Min Range: -4.5804

Max Act: 4.4674. Min Act: -0.1700

Data Index: 2902409 (Open Web Text)

Max Activating Token Index: 304

Text #3

Max Range: 4.5804. Min Range: -4.5804

Max Act: 4.4655. Min Act: -0.1700

Data Index: 4049976 (Open Web Text)

Max Activating Token Index: 443

Text #4

Max Range: 4.5804. Min Range: -4.5804

Max Act: 4.4366. Min Act: -0.1700

Data Index: 5368700 (Open Web Text)

Max Activating Token Index: 784

Text #5

Max Range: 4.5804. Min Range: -4.5804

Max Act: 4.4442. Min Act: -0.1700

Data Index: 575076 (Open Web Text)

Max Activating Token Index: 457

Text #6

Max Range: 4.5804. Min Range: -4.5804

Max Act: 4.4229. Min Act: -0.1700

Data Index: 4683476 (Open Web Text)

Max Activating Token Index: 1017

Text #7

Max Range: 4.5804. Min Range: -4.5804

Max Act: 4.4442. Min Act: -0.1700

Data Index: 1034014 (Open Web Text)

Max Activating Token Index: 395

Text #8

Max Range: 4.5804. Min Range: -4.5804

Max Act: 4.3886. Min Act: -0.1700

Data Index: 8411985 (Open Web Text)

Max Activating Token Index: 259

Text #9

Max Range: 4.5804. Min Range: -4.5804

Max Act: 4.3957. Min Act: -0.1700

Data Index: 2188896 (Open Web Text)

Max Activating Token Index: 150

Text #10

Max Range: 4.5804. Min Range: -4.5804

Max Act: 4.3810. Min Act: -0.1700

Data Index: 5302136 (Open Web Text)

Max Activating Token Index: 885

Text #11

Max Range: 4.5804. Min Range: -4.5804

Max Act: 4.3790. Min Act: -0.1700

Data Index: 6739478 (Open Web Text)

Max Activating Token Index: 912

Text #12

Max Range: 4.5804. Min Range: -4.5804

Max Act: 4.3825. Min Act: -0.1700

Data Index: 2443030 (Open Web Text)

Max Activating Token Index: 522

Text #13

Max Range: 4.5804. Min Range: -4.5804

Max Act: 4.3782. Min Act: -0.1700

Data Index: 1417172 (Open Web Text)

Max Activating Token Index: 761

Text #14

Max Range: 4.5804. Min Range: -4.5804

Max Act: 4.3910. Min Act: -0.1700

Data Index: 6225383 (Open Web Text)

Max Activating Token Index: 598

Text #15

Max Range: 4.5804. Min Range: -4.5804

Max Act: 4.3761. Min Act: -0.1700

Data Index: 2287191 (Open Web Text)

Max Activating Token Index: 632

Text #16

Max Range: 4.5804. Min Range: -4.5804

Max Act: 4.3645. Min Act: -0.1700

Data Index: 1320222 (Open Web Text)

Max Activating Token Index: 916

Text #17

Max Range: 4.5804. Min Range: -4.5804

Max Act: 4.3624. Min Act: -0.1700

Data Index: 3015233 (Open Web Text)

Max Activating Token Index: 930

Text #18

Max Range: 4.5804. Min Range: -4.5804

Max Act: 4.3280. Min Act: -0.1700

Data Index: 2704116 (Open Web Text)

Max Activating Token Index: 853

Text #19

Max Range: 4.5804. Min Range: -4.5804

Max Act: 4.3593. Min Act: -0.1700

Data Index: 4557987 (Open Web Text)

Max Activating Token Index: 982