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

Dataset: Open Web Text

Neuron 538 in Layer 1

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: 4.6666. Min Range: -4.6666

Max Act: 4.6666. Min Act: -0.1700

Data Index: 6320367 (Open Web Text)

Max Activating Token Index: 421

Text #1

Max Range: 4.6666. Min Range: -4.6666

Max Act: 4.6633. Min Act: -0.1700

Data Index: 2761858 (Open Web Text)

Max Activating Token Index: 558

Text #2

Max Range: 4.6666. Min Range: -4.6666

Max Act: 4.6129. Min Act: -0.1700

Data Index: 2420990 (Open Web Text)

Max Activating Token Index: 223

Text #3

Max Range: 4.6666. Min Range: -4.6666

Max Act: 4.5905. Min Act: -0.1700

Data Index: 3185347 (Open Web Text)

Max Activating Token Index: 85

Text #4

Max Range: 4.6666. Min Range: -4.6666

Max Act: 4.5963. Min Act: -0.1700

Data Index: 2415692 (Open Web Text)

Max Activating Token Index: 964

Text #5

Max Range: 4.6666. Min Range: -4.6666

Max Act: 4.5526. Min Act: -0.1700

Data Index: 8165808 (Open Web Text)

Max Activating Token Index: 322

Text #6

Max Range: 4.6666. Min Range: -4.6666

Max Act: 4.5474. Min Act: -0.1700

Data Index: 6583675 (Open Web Text)

Max Activating Token Index: 399

Text #7

Max Range: 4.6666. Min Range: -4.6666

Max Act: 4.5267. Min Act: -0.1700

Data Index: 3628269 (Open Web Text)

Max Activating Token Index: 610

Text #8

Max Range: 4.6666. Min Range: -4.6666

Max Act: 4.5095. Min Act: -0.1700

Data Index: 342473 (Open Web Text)

Max Activating Token Index: 284

Text #9

Max Range: 4.6666. Min Range: -4.6666

Max Act: 4.5488. Min Act: -0.1700

Data Index: 8416797 (Open Web Text)

Max Activating Token Index: 608

Text #10

Max Range: 4.6666. Min Range: -4.6666

Max Act: 4.4847. Min Act: -0.1700

Data Index: 8367921 (Open Web Text)

Max Activating Token Index: 196

Text #11

Max Range: 4.6666. Min Range: -4.6666

Max Act: 4.4977. Min Act: -0.1700

Data Index: 7160174 (Open Web Text)

Max Activating Token Index: 399

Text #12

Max Range: 4.6666. Min Range: -4.6666

Max Act: 4.4861. Min Act: -0.1700

Data Index: 227699 (Open Web Text)

Max Activating Token Index: 139

Text #13

Max Range: 4.6666. Min Range: -4.6666

Max Act: 4.5125. Min Act: -0.1700

Data Index: 2841744 (Open Web Text)

Max Activating Token Index: 951

Text #14

Max Range: 4.6666. Min Range: -4.6666

Max Act: 4.4618. Min Act: -0.1700

Data Index: 3737305 (Open Web Text)

Max Activating Token Index: 645

Text #15

Max Range: 4.6666. Min Range: -4.6666

Max Act: 4.4738. Min Act: -0.1700

Data Index: 7449803 (Open Web Text)

Max Activating Token Index: 652

Text #16

Max Range: 4.6666. Min Range: -4.6666

Max Act: 4.4832. Min Act: -0.1700

Data Index: 7428297 (Open Web Text)

Max Activating Token Index: 92

Text #17

Max Range: 4.6666. Min Range: -4.6666

Max Act: 4.4687. Min Act: -0.1700

Data Index: 6237410 (Open Web Text)

Max Activating Token Index: 341

Text #18

Max Range: 4.6666. Min Range: -4.6666

Max Act: 4.4572. Min Act: -0.1700

Data Index: 8627621 (Open Web Text)

Max Activating Token Index: 332

Text #19

Max Range: 4.6666. Min Range: -4.6666

Max Act: 4.4100. Min Act: -0.1700

Data Index: 7474104 (Open Web Text)

Max Activating Token Index: 456