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

Dataset: Open Web Text

Neuron 811 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: 3.6576. Min Range: -3.6576

Max Act: 3.6576. Min Act: -0.1700

Data Index: 5545548 (Open Web Text)

Max Activating Token Index: 148

Text #1

Max Range: 3.6576. Min Range: -3.6576

Max Act: 3.4850. Min Act: -0.1700

Data Index: 2507472 (Open Web Text)

Max Activating Token Index: 611

Text #2

Max Range: 3.6576. Min Range: -3.6576

Max Act: 3.4128. Min Act: -0.1700

Data Index: 7925494 (Open Web Text)

Max Activating Token Index: 881

Text #3

Max Range: 3.6576. Min Range: -3.6576

Max Act: 3.4006. Min Act: -0.1700

Data Index: 5183424 (Open Web Text)

Max Activating Token Index: 737

Text #4

Max Range: 3.6576. Min Range: -3.6576

Max Act: 3.3276. Min Act: -0.1700

Data Index: 7342686 (Open Web Text)

Max Activating Token Index: 384

Text #5

Max Range: 3.6576. Min Range: -3.6576

Max Act: 3.2695. Min Act: -0.1700

Data Index: 713854 (Open Web Text)

Max Activating Token Index: 792

Text #6

Max Range: 3.6576. Min Range: -3.6576

Max Act: 3.2544. Min Act: -0.1700

Data Index: 657033 (Open Web Text)

Max Activating Token Index: 470

Text #7

Max Range: 3.6576. Min Range: -3.6576

Max Act: 3.2105. Min Act: -0.1700

Data Index: 143342 (Open Web Text)

Max Activating Token Index: 708

Text #8

Max Range: 3.6576. Min Range: -3.6576

Max Act: 3.3059. Min Act: -0.1700

Data Index: 1562969 (Open Web Text)

Max Activating Token Index: 666

Text #9

Max Range: 3.6576. Min Range: -3.6576

Max Act: 3.2058. Min Act: -0.1700

Data Index: 3067739 (Open Web Text)

Max Activating Token Index: 868

Text #10

Max Range: 3.6576. Min Range: -3.6576

Max Act: 3.2320. Min Act: -0.1700

Data Index: 7256147 (Open Web Text)

Max Activating Token Index: 277

Text #11

Max Range: 3.6576. Min Range: -3.6576

Max Act: 3.2179. Min Act: -0.1700

Data Index: 2384383 (Open Web Text)

Max Activating Token Index: 206

Text #12

Max Range: 3.6576. Min Range: -3.6576

Max Act: 3.2077. Min Act: -0.1700

Data Index: 5897957 (Open Web Text)

Max Activating Token Index: 434

Text #13

Max Range: 3.6576. Min Range: -3.6576

Max Act: 3.2135. Min Act: -0.1700

Data Index: 528310 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.6576. Min Range: -3.6576

Max Act: 3.1836. Min Act: -0.1700

Data Index: 1368816 (Open Web Text)

Max Activating Token Index: 233

Text #15

Max Range: 3.6576. Min Range: -3.6576

Max Act: 3.1918. Min Act: -0.1700

Data Index: 5896358 (Open Web Text)

Max Activating Token Index: 70

Text #16

Max Range: 3.6576. Min Range: -3.6576

Max Act: 3.1688. Min Act: -0.1700

Data Index: 2128430 (Open Web Text)

Max Activating Token Index: 588

Text #17

Max Range: 3.6576. Min Range: -3.6576

Max Act: 3.2093. Min Act: -0.1700

Data Index: 5431639 (Open Web Text)

Max Activating Token Index: 546

Text #18

Max Range: 3.6576. Min Range: -3.6576

Max Act: 3.2609. Min Act: -0.1700

Data Index: 7801300 (Open Web Text)

Max Activating Token Index: 437

Text #19

Max Range: 3.6576. Min Range: -3.6576

Max Act: 3.1840. Min Act: -0.1700

Data Index: 4016976 (Open Web Text)

Max Activating Token Index: 184