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

Dataset: Open Web Text

Neuron 605 in Layer 6

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: 4.0487. Min Range: -4.0487

Max Act: 4.0487. Min Act: -0.1700

Data Index: 6284507 (Open Web Text)

Max Activating Token Index: 945

Text #1

Max Range: 4.0487. Min Range: -4.0487

Max Act: 4.0086. Min Act: -0.1700

Data Index: 2212577 (Open Web Text)

Max Activating Token Index: 998

Text #2

Max Range: 4.0487. Min Range: -4.0487

Max Act: 3.9548. Min Act: -0.1700

Data Index: 2872782 (Open Web Text)

Max Activating Token Index: 717

Text #3

Max Range: 4.0487. Min Range: -4.0487

Max Act: 3.9494. Min Act: -0.1700

Data Index: 2537410 (Open Web Text)

Max Activating Token Index: 227

Text #4

Max Range: 4.0487. Min Range: -4.0487

Max Act: 3.8814. Min Act: -0.1700

Data Index: 1546967 (Open Web Text)

Max Activating Token Index: 960

Text #5

Max Range: 4.0487. Min Range: -4.0487

Max Act: 3.9179. Min Act: -0.1700

Data Index: 2577024 (Open Web Text)

Max Activating Token Index: 277

Text #6

Max Range: 4.0487. Min Range: -4.0487

Max Act: 3.8770. Min Act: -0.1700

Data Index: 8303426 (Open Web Text)

Max Activating Token Index: 292

Text #7

Max Range: 4.0487. Min Range: -4.0487

Max Act: 3.8506. Min Act: -0.1700

Data Index: 6827277 (Open Web Text)

Max Activating Token Index: 166

Text #8

Max Range: 4.0487. Min Range: -4.0487

Max Act: 3.8163. Min Act: -0.1700

Data Index: 7665464 (Open Web Text)

Max Activating Token Index: 103

Text #9

Max Range: 4.0487. Min Range: -4.0487

Max Act: 3.8288. Min Act: -0.1700

Data Index: 2126433 (Open Web Text)

Max Activating Token Index: 383

Text #10

Max Range: 4.0487. Min Range: -4.0487

Max Act: 3.8623. Min Act: -0.1700

Data Index: 4140565 (Open Web Text)

Max Activating Token Index: 878

Text #11

Max Range: 4.0487. Min Range: -4.0487

Max Act: 3.8527. Min Act: -0.1700

Data Index: 1355542 (Open Web Text)

Max Activating Token Index: 941

Text #12

Max Range: 4.0487. Min Range: -4.0487

Max Act: 3.8377. Min Act: -0.1700

Data Index: 1975068 (Open Web Text)

Max Activating Token Index: 262

Text #13

Max Range: 4.0487. Min Range: -4.0487

Max Act: 3.8132. Min Act: -0.1700

Data Index: 3535054 (Open Web Text)

Max Activating Token Index: 781

Text #14

Max Range: 4.0487. Min Range: -4.0487

Max Act: 3.7903. Min Act: -0.1700

Data Index: 6447222 (Open Web Text)

Max Activating Token Index: 715

Text #15

Max Range: 4.0487. Min Range: -4.0487

Max Act: 3.7950. Min Act: -0.1700

Data Index: 6269608 (Open Web Text)

Max Activating Token Index: 33

Text #16

Max Range: 4.0487. Min Range: -4.0487

Max Act: 3.8337. Min Act: -0.1700

Data Index: 8020206 (Open Web Text)

Max Activating Token Index: 776

Text #17

Max Range: 4.0487. Min Range: -4.0487

Max Act: 3.7839. Min Act: -0.1700

Data Index: 843590 (Open Web Text)

Max Activating Token Index: 818

Text #18

Max Range: 4.0487. Min Range: -4.0487

Max Act: 3.8220. Min Act: -0.1700

Data Index: 3757070 (Open Web Text)

Max Activating Token Index: 529

Text #19

Max Range: 4.0487. Min Range: -4.0487

Max Act: 3.7791. Min Act: -0.1700

Data Index: 6610466 (Open Web Text)

Max Activating Token Index: 500