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

Dataset: Open Web Text

Neuron 1556 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: 4.3916. Min Range: -4.3916

Max Act: 4.3578. Min Act: -0.1700

Data Index: 2491154 (Open Web Text)

Max Activating Token Index: 497

Text #1

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.3536. Min Act: -0.1700

Data Index: 4952809 (Open Web Text)

Max Activating Token Index: 608

Text #2

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.3719. Min Act: -0.1700

Data Index: 6447136 (Open Web Text)

Max Activating Token Index: 448

Text #3

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.3916. Min Act: -0.1700

Data Index: 3261549 (Open Web Text)

Max Activating Token Index: 774

Text #4

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.3549. Min Act: -0.1700

Data Index: 8780077 (Open Web Text)

Max Activating Token Index: 926

Text #5

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.3398. Min Act: -0.1700

Data Index: 7369839 (Open Web Text)

Max Activating Token Index: 665

Text #6

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.2877. Min Act: -0.1700

Data Index: 5987055 (Open Web Text)

Max Activating Token Index: 610

Text #7

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.2936. Min Act: -0.1700

Data Index: 3955248 (Open Web Text)

Max Activating Token Index: 713

Text #8

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.2914. Min Act: -0.1700

Data Index: 3939382 (Open Web Text)

Max Activating Token Index: 958

Text #9

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.3127. Min Act: -0.1700

Data Index: 5577419 (Open Web Text)

Max Activating Token Index: 359

Text #10

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.2778. Min Act: -0.1700

Data Index: 3321619 (Open Web Text)

Max Activating Token Index: 443

Text #11

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.2460. Min Act: -0.1700

Data Index: 7668425 (Open Web Text)

Max Activating Token Index: 935

Text #12

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.2499. Min Act: -0.1700

Data Index: 5309542 (Open Web Text)

Max Activating Token Index: 471

Text #13

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.2518. Min Act: -0.1700

Data Index: 453129 (Open Web Text)

Max Activating Token Index: 293

Text #14

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.2235. Min Act: -0.1700

Data Index: 5270177 (Open Web Text)

Max Activating Token Index: 576

Text #15

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.2573. Min Act: -0.1700

Data Index: 320567 (Open Web Text)

Max Activating Token Index: 400

Text #16

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.2265. Min Act: -0.1700

Data Index: 4499469 (Open Web Text)

Max Activating Token Index: 722

Text #17

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.2554. Min Act: -0.1700

Data Index: 5582192 (Open Web Text)

Max Activating Token Index: 178

Text #18

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.2258. Min Act: -0.1700

Data Index: 5673451 (Open Web Text)

Max Activating Token Index: 994

Text #19

Max Range: 4.3916. Min Range: -4.3916

Max Act: 4.2501. Min Act: -0.1700

Data Index: 3125764 (Open Web Text)

Max Activating Token Index: 733