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

Dataset: Open Web Text

Neuron 2230 in Layer 4

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: 3.4172. Min Range: -3.4172

Max Act: 3.4172. Min Act: -0.1700

Data Index: 6665212 (Open Web Text)

Max Activating Token Index: 193

Text #1

Max Range: 3.4172. Min Range: -3.4172

Max Act: 3.2601. Min Act: -0.1700

Data Index: 3389421 (Open Web Text)

Max Activating Token Index: 102

Text #2

Max Range: 3.4172. Min Range: -3.4172

Max Act: 3.1428. Min Act: -0.1700

Data Index: 7678524 (Open Web Text)

Max Activating Token Index: 720

Text #3

Max Range: 3.4172. Min Range: -3.4172

Max Act: 3.1963. Min Act: -0.1700

Data Index: 6575849 (Open Web Text)

Max Activating Token Index: 166

Text #4

Max Range: 3.4172. Min Range: -3.4172

Max Act: 3.1731. Min Act: -0.1700

Data Index: 4716477 (Open Web Text)

Max Activating Token Index: 24

Text #5

Max Range: 3.4172. Min Range: -3.4172

Max Act: 3.1423. Min Act: -0.1700

Data Index: 1662067 (Open Web Text)

Max Activating Token Index: 993

Text #6

Max Range: 3.4172. Min Range: -3.4172

Max Act: 3.1193. Min Act: -0.1700

Data Index: 8013600 (Open Web Text)

Max Activating Token Index: 859

Text #7

Max Range: 3.4172. Min Range: -3.4172

Max Act: 3.1438. Min Act: -0.1700

Data Index: 6911168 (Open Web Text)

Max Activating Token Index: 824

Text #8

Max Range: 3.4172. Min Range: -3.4172

Max Act: 3.1264. Min Act: -0.1700

Data Index: 4994049 (Open Web Text)

Max Activating Token Index: 313

Text #9

Max Range: 3.4172. Min Range: -3.4172

Max Act: 3.0870. Min Act: -0.1700

Data Index: 2159321 (Open Web Text)

Max Activating Token Index: 194

Text #10

Max Range: 3.4172. Min Range: -3.4172

Max Act: 3.0732. Min Act: -0.1700

Data Index: 955685 (Open Web Text)

Max Activating Token Index: 571

Text #11

Max Range: 3.4172. Min Range: -3.4172

Max Act: 3.1164. Min Act: -0.1700

Data Index: 654912 (Open Web Text)

Max Activating Token Index: 786

Text #12

Max Range: 3.4172. Min Range: -3.4172

Max Act: 3.0734. Min Act: -0.1700

Data Index: 5119401 (Open Web Text)

Max Activating Token Index: 99

Text #13

Max Range: 3.4172. Min Range: -3.4172

Max Act: 3.1151. Min Act: -0.1700

Data Index: 2736470 (Open Web Text)

Max Activating Token Index: 915

Text #14

Max Range: 3.4172. Min Range: -3.4172

Max Act: 3.1258. Min Act: -0.1700

Data Index: 7708075 (Open Web Text)

Max Activating Token Index: 903

Text #15

Max Range: 3.4172. Min Range: -3.4172

Max Act: 3.0797. Min Act: -0.1700

Data Index: 3795347 (Open Web Text)

Max Activating Token Index: 611

Text #16

Max Range: 3.4172. Min Range: -3.4172

Max Act: 3.0638. Min Act: -0.1700

Data Index: 3590916 (Open Web Text)

Max Activating Token Index: 369

Text #17

Max Range: 3.4172. Min Range: -3.4172

Max Act: 3.1211. Min Act: -0.1700

Data Index: 7757554 (Open Web Text)

Max Activating Token Index: 684

Text #18

Max Range: 3.4172. Min Range: -3.4172

Max Act: 3.0849. Min Act: -0.1700

Data Index: 3229677 (Open Web Text)

Max Activating Token Index: 360

Text #19

Max Range: 3.4172. Min Range: -3.4172

Max Act: 3.0567. Min Act: -0.1700

Data Index: 3953500 (Open Web Text)

Max Activating Token Index: 354