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

Dataset: Open Web Text

Neuron 2112 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: 4.6349. Min Range: -4.6349

Max Act: 4.6200. Min Act: -0.1700

Data Index: 3700836 (Open Web Text)

Max Activating Token Index: 313

Text #1

Max Range: 4.6349. Min Range: -4.6349

Max Act: 4.6298. Min Act: -0.1700

Data Index: 7313666 (Open Web Text)

Max Activating Token Index: 25

Text #2

Max Range: 4.6349. Min Range: -4.6349

Max Act: 4.6349. Min Act: -0.1700

Data Index: 7626660 (Open Web Text)

Max Activating Token Index: 11

Text #3

Max Range: 4.6349. Min Range: -4.6349

Max Act: 4.5947. Min Act: -0.1700

Data Index: 201670 (Open Web Text)

Max Activating Token Index: 975

Text #4

Max Range: 4.6349. Min Range: -4.6349

Max Act: 4.5765. Min Act: -0.1700

Data Index: 849073 (Open Web Text)

Max Activating Token Index: 91

Text #5

Max Range: 4.6349. Min Range: -4.6349

Max Act: 4.5720. Min Act: -0.1700

Data Index: 120494 (Open Web Text)

Max Activating Token Index: 18

Text #6

Max Range: 4.6349. Min Range: -4.6349

Max Act: 4.5613. Min Act: -0.1700

Data Index: 2780566 (Open Web Text)

Max Activating Token Index: 107

Text #7

Max Range: 4.6349. Min Range: -4.6349

Max Act: 4.5599. Min Act: -0.1700

Data Index: 3979640 (Open Web Text)

Max Activating Token Index: 56

Text #8

Max Range: 4.6349. Min Range: -4.6349

Max Act: 4.5529. Min Act: -0.1700

Data Index: 5107331 (Open Web Text)

Max Activating Token Index: 362

Text #9

Max Range: 4.6349. Min Range: -4.6349

Max Act: 4.5539. Min Act: -0.1700

Data Index: 7463848 (Open Web Text)

Max Activating Token Index: 44

Text #10

Max Range: 4.6349. Min Range: -4.6349

Max Act: 4.5179. Min Act: -0.1700

Data Index: 648699 (Open Web Text)

Max Activating Token Index: 25

Text #11

Max Range: 4.6349. Min Range: -4.6349

Max Act: 4.5090. Min Act: -0.1700

Data Index: 3700837 (Open Web Text)

Max Activating Token Index: 187

Text #12

Max Range: 4.6349. Min Range: -4.6349

Max Act: 4.4895. Min Act: -0.1700

Data Index: 651402 (Open Web Text)

Max Activating Token Index: 462

Text #13

Max Range: 4.6349. Min Range: -4.6349

Max Act: 4.5454. Min Act: -0.1700

Data Index: 2014830 (Open Web Text)

Max Activating Token Index: 1005

Text #14

Max Range: 4.6349. Min Range: -4.6349

Max Act: 4.4909. Min Act: -0.1700

Data Index: 4992357 (Open Web Text)

Max Activating Token Index: 890

Text #15

Max Range: 4.6349. Min Range: -4.6349

Max Act: 4.4780. Min Act: -0.1700

Data Index: 3670500 (Open Web Text)

Max Activating Token Index: 964

Text #16

Max Range: 4.6349. Min Range: -4.6349

Max Act: 4.4931. Min Act: -0.1700

Data Index: 6539978 (Open Web Text)

Max Activating Token Index: 233

Text #17

Max Range: 4.6349. Min Range: -4.6349

Max Act: 4.4782. Min Act: -0.1700

Data Index: 5534394 (Open Web Text)

Max Activating Token Index: 100

Text #18

Max Range: 4.6349. Min Range: -4.6349

Max Act: 4.4202. Min Act: -0.1700

Data Index: 4382965 (Open Web Text)

Max Activating Token Index: 946

Text #19

Max Range: 4.6349. Min Range: -4.6349

Max Act: 4.4428. Min Act: -0.1700

Data Index: 4955761 (Open Web Text)

Max Activating Token Index: 11