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

Dataset: Open Web Text

Neuron 1503 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: 4.1497. Min Range: -4.1497

Max Act: 4.1497. Min Act: -0.1700

Data Index: 4500279 (Open Web Text)

Max Activating Token Index: 926

Text #1

Max Range: 4.1497. Min Range: -4.1497

Max Act: 4.0215. Min Act: -0.1700

Data Index: 7126913 (Open Web Text)

Max Activating Token Index: 801

Text #2

Max Range: 4.1497. Min Range: -4.1497

Max Act: 4.0238. Min Act: -0.1700

Data Index: 6712874 (Open Web Text)

Max Activating Token Index: 326

Text #3

Max Range: 4.1497. Min Range: -4.1497

Max Act: 3.9857. Min Act: -0.1700

Data Index: 7512400 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.1497. Min Range: -4.1497

Max Act: 3.9784. Min Act: -0.1700

Data Index: 6767457 (Open Web Text)

Max Activating Token Index: 437

Text #5

Max Range: 4.1497. Min Range: -4.1497

Max Act: 3.9669. Min Act: -0.1700

Data Index: 8593753 (Open Web Text)

Max Activating Token Index: 752

Text #6

Max Range: 4.1497. Min Range: -4.1497

Max Act: 3.9430. Min Act: -0.1700

Data Index: 4079756 (Open Web Text)

Max Activating Token Index: 719

Text #7

Max Range: 4.1497. Min Range: -4.1497

Max Act: 3.9307. Min Act: -0.1700

Data Index: 7297178 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.1497. Min Range: -4.1497

Max Act: 3.9312. Min Act: -0.1700

Data Index: 8323730 (Open Web Text)

Max Activating Token Index: 142

Text #9

Max Range: 4.1497. Min Range: -4.1497

Max Act: 3.8910. Min Act: -0.1700

Data Index: 7967377 (Open Web Text)

Max Activating Token Index: 201

Text #10

Max Range: 4.1497. Min Range: -4.1497

Max Act: 3.8991. Min Act: -0.1700

Data Index: 176013 (Open Web Text)

Max Activating Token Index: 438

Text #11

Max Range: 4.1497. Min Range: -4.1497

Max Act: 3.9087. Min Act: -0.1700

Data Index: 6511790 (Open Web Text)

Max Activating Token Index: 209

Text #12

Max Range: 4.1497. Min Range: -4.1497

Max Act: 3.9073. Min Act: -0.1700

Data Index: 5431181 (Open Web Text)

Max Activating Token Index: 483

Text #13

Max Range: 4.1497. Min Range: -4.1497

Max Act: 3.9115. Min Act: -0.1700

Data Index: 997808 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 4.1497. Min Range: -4.1497

Max Act: 3.9098. Min Act: -0.1700

Data Index: 7369225 (Open Web Text)

Max Activating Token Index: 150

Text #15

Max Range: 4.1497. Min Range: -4.1497

Max Act: 3.8892. Min Act: -0.1700

Data Index: 4419769 (Open Web Text)

Max Activating Token Index: 33

Text #16

Max Range: 4.1497. Min Range: -4.1497

Max Act: 3.9286. Min Act: -0.1700

Data Index: 3245642 (Open Web Text)

Max Activating Token Index: 11

Text #17

Max Range: 4.1497. Min Range: -4.1497

Max Act: 3.8614. Min Act: -0.1700

Data Index: 828886 (Open Web Text)

Max Activating Token Index: 1009

Text #18

Max Range: 4.1497. Min Range: -4.1497

Max Act: 3.8822. Min Act: -0.1700

Data Index: 6667301 (Open Web Text)

Max Activating Token Index: 733

Text #19

Max Range: 4.1497. Min Range: -4.1497

Max Act: 3.8764. Min Act: -0.1700

Data Index: 740588 (Open Web Text)

Max Activating Token Index: 718