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

Dataset: Open Web Text

Neuron 600 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: 6.1143. Min Range: -6.1143

Max Act: 6.0903. Min Act: -0.1700

Data Index: 6393388 (Open Web Text)

Max Activating Token Index: 776

Text #1

Max Range: 6.1143. Min Range: -6.1143

Max Act: 6.1143. Min Act: -0.1700

Data Index: 779939 (Open Web Text)

Max Activating Token Index: 998

Text #2

Max Range: 6.1143. Min Range: -6.1143

Max Act: 6.0506. Min Act: -0.1700

Data Index: 6639727 (Open Web Text)

Max Activating Token Index: 932

Text #3

Max Range: 6.1143. Min Range: -6.1143

Max Act: 5.9687. Min Act: -0.1700

Data Index: 7244988 (Open Web Text)

Max Activating Token Index: 240

Text #4

Max Range: 6.1143. Min Range: -6.1143

Max Act: 5.9319. Min Act: -0.1700

Data Index: 6059181 (Open Web Text)

Max Activating Token Index: 542

Text #5

Max Range: 6.1143. Min Range: -6.1143

Max Act: 5.8310. Min Act: -0.1700

Data Index: 4944786 (Open Web Text)

Max Activating Token Index: 910

Text #6

Max Range: 6.1143. Min Range: -6.1143

Max Act: 5.7828. Min Act: -0.1700

Data Index: 6380098 (Open Web Text)

Max Activating Token Index: 242

Text #7

Max Range: 6.1143. Min Range: -6.1143

Max Act: 5.8099. Min Act: -0.1700

Data Index: 2971580 (Open Web Text)

Max Activating Token Index: 630

Text #8

Max Range: 6.1143. Min Range: -6.1143

Max Act: 5.7831. Min Act: -0.1700

Data Index: 7309532 (Open Web Text)

Max Activating Token Index: 781

Text #9

Max Range: 6.1143. Min Range: -6.1143

Max Act: 5.7757. Min Act: -0.1700

Data Index: 1058998 (Open Web Text)

Max Activating Token Index: 997

Text #10

Max Range: 6.1143. Min Range: -6.1143

Max Act: 5.7502. Min Act: -0.1700

Data Index: 3699813 (Open Web Text)

Max Activating Token Index: 141

Text #11

Max Range: 6.1143. Min Range: -6.1143

Max Act: 5.7612. Min Act: -0.1700

Data Index: 5065388 (Open Web Text)

Max Activating Token Index: 457

Text #12

Max Range: 6.1143. Min Range: -6.1143

Max Act: 5.7402. Min Act: -0.1700

Data Index: 3833014 (Open Web Text)

Max Activating Token Index: 1020

Text #13

Max Range: 6.1143. Min Range: -6.1143

Max Act: 5.6974. Min Act: -0.1700

Data Index: 4363905 (Open Web Text)

Max Activating Token Index: 696

Text #14

Max Range: 6.1143. Min Range: -6.1143

Max Act: 5.7253. Min Act: -0.1700

Data Index: 4395268 (Open Web Text)

Max Activating Token Index: 175

Text #15

Max Range: 6.1143. Min Range: -6.1143

Max Act: 5.6850. Min Act: -0.1700

Data Index: 3210464 (Open Web Text)

Max Activating Token Index: 339

Text #16

Max Range: 6.1143. Min Range: -6.1143

Max Act: 5.7335. Min Act: -0.1700

Data Index: 5594589 (Open Web Text)

Max Activating Token Index: 56

Text #17

Max Range: 6.1143. Min Range: -6.1143

Max Act: 5.6900. Min Act: -0.1700

Data Index: 3898186 (Open Web Text)

Max Activating Token Index: 402

Text #18

Max Range: 6.1143. Min Range: -6.1143

Max Act: 5.7233. Min Act: -0.1700

Data Index: 7234182 (Open Web Text)

Max Activating Token Index: 341

Text #19

Max Range: 6.1143. Min Range: -6.1143

Max Act: 5.7153. Min Act: -0.1700

Data Index: 5868614 (Open Web Text)

Max Activating Token Index: 736