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

Dataset: Open Web Text

Neuron 2013 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: 4.0932. Min Range: -4.0932

Max Act: 4.0932. Min Act: -0.1700

Data Index: 4450121 (Open Web Text)

Max Activating Token Index: 384

Text #1

Max Range: 4.0932. Min Range: -4.0932

Max Act: 4.0104. Min Act: -0.1700

Data Index: 2906689 (Open Web Text)

Max Activating Token Index: 345

Text #2

Max Range: 4.0932. Min Range: -4.0932

Max Act: 3.9812. Min Act: -0.1700

Data Index: 5708601 (Open Web Text)

Max Activating Token Index: 901

Text #3

Max Range: 4.0932. Min Range: -4.0932

Max Act: 3.9595. Min Act: -0.1700

Data Index: 723651 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 4.0932. Min Range: -4.0932

Max Act: 3.9218. Min Act: -0.1700

Data Index: 2376783 (Open Web Text)

Max Activating Token Index: 533

Text #5

Max Range: 4.0932. Min Range: -4.0932

Max Act: 3.9274. Min Act: -0.1700

Data Index: 2426221 (Open Web Text)

Max Activating Token Index: 381

Text #6

Max Range: 4.0932. Min Range: -4.0932

Max Act: 3.9230. Min Act: -0.1700

Data Index: 207864 (Open Web Text)

Max Activating Token Index: 1018

Text #7

Max Range: 4.0932. Min Range: -4.0932

Max Act: 3.8729. Min Act: -0.1700

Data Index: 2102736 (Open Web Text)

Max Activating Token Index: 183

Text #8

Max Range: 4.0932. Min Range: -4.0932

Max Act: 3.8510. Min Act: -0.1700

Data Index: 3842502 (Open Web Text)

Max Activating Token Index: 990

Text #9

Max Range: 4.0932. Min Range: -4.0932

Max Act: 3.8525. Min Act: -0.1700

Data Index: 8173385 (Open Web Text)

Max Activating Token Index: 942

Text #10

Max Range: 4.0932. Min Range: -4.0932

Max Act: 3.8472. Min Act: -0.1700

Data Index: 6759349 (Open Web Text)

Max Activating Token Index: 663

Text #11

Max Range: 4.0932. Min Range: -4.0932

Max Act: 3.8575. Min Act: -0.1700

Data Index: 5050120 (Open Web Text)

Max Activating Token Index: 730

Text #12

Max Range: 4.0932. Min Range: -4.0932

Max Act: 3.8041. Min Act: -0.1700

Data Index: 2459217 (Open Web Text)

Max Activating Token Index: 833

Text #13

Max Range: 4.0932. Min Range: -4.0932

Max Act: 3.8329. Min Act: -0.1700

Data Index: 7344475 (Open Web Text)

Max Activating Token Index: 825

Text #14

Max Range: 4.0932. Min Range: -4.0932

Max Act: 3.8183. Min Act: -0.1700

Data Index: 2474733 (Open Web Text)

Max Activating Token Index: 74

Text #15

Max Range: 4.0932. Min Range: -4.0932

Max Act: 3.8264. Min Act: -0.1700

Data Index: 4084532 (Open Web Text)

Max Activating Token Index: 121

Text #16

Max Range: 4.0932. Min Range: -4.0932

Max Act: 3.7923. Min Act: -0.1700

Data Index: 2941282 (Open Web Text)

Max Activating Token Index: 237

Text #17

Max Range: 4.0932. Min Range: -4.0932

Max Act: 3.7951. Min Act: -0.1700

Data Index: 5230897 (Open Web Text)

Max Activating Token Index: 211

Text #18

Max Range: 4.0932. Min Range: -4.0932

Max Act: 3.7633. Min Act: -0.1700

Data Index: 4430473 (Open Web Text)

Max Activating Token Index: 781

Text #19

Max Range: 4.0932. Min Range: -4.0932

Max Act: 3.8170. Min Act: -0.1700

Data Index: 806780 (Open Web Text)

Max Activating Token Index: 437