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

Dataset: Open Web Text

Neuron 2147 in Layer 5

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: 5.7888. Min Range: -5.7888

Max Act: 5.7888. Min Act: -0.1700

Data Index: 6314675 (Open Web Text)

Max Activating Token Index: 643

Text #1

Max Range: 5.7888. Min Range: -5.7888

Max Act: 5.6116. Min Act: -0.1700

Data Index: 7187228 (Open Web Text)

Max Activating Token Index: 347

Text #2

Max Range: 5.7888. Min Range: -5.7888

Max Act: 5.4479. Min Act: -0.1700

Data Index: 6304878 (Open Web Text)

Max Activating Token Index: 243

Text #3

Max Range: 5.7888. Min Range: -5.7888

Max Act: 5.3811. Min Act: -0.1700

Data Index: 7776681 (Open Web Text)

Max Activating Token Index: 288

Text #4

Max Range: 5.7888. Min Range: -5.7888

Max Act: 5.3691. Min Act: -0.1700

Data Index: 3547558 (Open Web Text)

Max Activating Token Index: 808

Text #5

Max Range: 5.7888. Min Range: -5.7888

Max Act: 5.3654. Min Act: -0.1700

Data Index: 2589720 (Open Web Text)

Max Activating Token Index: 925

Text #6

Max Range: 5.7888. Min Range: -5.7888

Max Act: 5.3802. Min Act: -0.1700

Data Index: 257706 (Open Web Text)

Max Activating Token Index: 384

Text #7

Max Range: 5.7888. Min Range: -5.7888

Max Act: 5.3340. Min Act: -0.1700

Data Index: 7357970 (Open Web Text)

Max Activating Token Index: 932

Text #8

Max Range: 5.7888. Min Range: -5.7888

Max Act: 5.3168. Min Act: -0.1700

Data Index: 6994612 (Open Web Text)

Max Activating Token Index: 720

Text #9

Max Range: 5.7888. Min Range: -5.7888

Max Act: 5.3533. Min Act: -0.1700

Data Index: 3026582 (Open Web Text)

Max Activating Token Index: 648

Text #10

Max Range: 5.7888. Min Range: -5.7888

Max Act: 5.2999. Min Act: -0.1700

Data Index: 2088507 (Open Web Text)

Max Activating Token Index: 148

Text #11

Max Range: 5.7888. Min Range: -5.7888

Max Act: 5.2618. Min Act: -0.1700

Data Index: 1501613 (Open Web Text)

Max Activating Token Index: 568

Text #12

Max Range: 5.7888. Min Range: -5.7888

Max Act: 5.2716. Min Act: -0.1700

Data Index: 6631453 (Open Web Text)

Max Activating Token Index: 680

Text #13

Max Range: 5.7888. Min Range: -5.7888

Max Act: 5.2799. Min Act: -0.1700

Data Index: 2654527 (Open Web Text)

Max Activating Token Index: 723

Text #14

Max Range: 5.7888. Min Range: -5.7888

Max Act: 5.2698. Min Act: -0.1700

Data Index: 1257995 (Open Web Text)

Max Activating Token Index: 192

Text #15

Max Range: 5.7888. Min Range: -5.7888

Max Act: 5.2928. Min Act: -0.1700

Data Index: 5899967 (Open Web Text)

Max Activating Token Index: 26

Text #16

Max Range: 5.7888. Min Range: -5.7888

Max Act: 5.2839. Min Act: -0.1700

Data Index: 7014668 (Open Web Text)

Max Activating Token Index: 563

Text #17

Max Range: 5.7888. Min Range: -5.7888

Max Act: 5.2566. Min Act: -0.1700

Data Index: 4137006 (Open Web Text)

Max Activating Token Index: 861

Text #18

Max Range: 5.7888. Min Range: -5.7888

Max Act: 5.2393. Min Act: -0.1700

Data Index: 2270672 (Open Web Text)

Max Activating Token Index: 709

Text #19

Max Range: 5.7888. Min Range: -5.7888

Max Act: 5.2476. Min Act: -0.1700

Data Index: 2381353 (Open Web Text)

Max Activating Token Index: 478