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

Dataset: Open Web Text

Neuron 1618 in Layer 0

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: 1.6054. Min Range: -1.6054

Max Act: 1.6054. Min Act: -0.1624

Data Index: 1536190 (Open Web Text)

Max Activating Token Index: 63

Text #1

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.5075. Min Act: -0.1657

Data Index: 7828917 (Open Web Text)

Max Activating Token Index: 133

Text #2

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.5196. Min Act: -0.1689

Data Index: 6745816 (Open Web Text)

Max Activating Token Index: 404

Text #3

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.5076. Min Act: -0.1634

Data Index: 6317292 (Open Web Text)

Max Activating Token Index: 13

Text #4

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.4969. Min Act: -0.1684

Data Index: 7926741 (Open Web Text)

Max Activating Token Index: 299

Text #5

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.5036. Min Act: -0.1700

Data Index: 1452858 (Open Web Text)

Max Activating Token Index: 259

Text #6

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.4833. Min Act: -0.1688

Data Index: 592021 (Open Web Text)

Max Activating Token Index: 150

Text #7

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.4844. Min Act: -0.1682

Data Index: 2194034 (Open Web Text)

Max Activating Token Index: 19

Text #8

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.4878. Min Act: -0.1691

Data Index: 3176898 (Open Web Text)

Max Activating Token Index: 279

Text #9

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.4924. Min Act: -0.1636

Data Index: 5845740 (Open Web Text)

Max Activating Token Index: 283

Text #10

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.4907. Min Act: -0.1698

Data Index: 3058363 (Open Web Text)

Max Activating Token Index: 263

Text #11

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.4864. Min Act: -0.1664

Data Index: 8661386 (Open Web Text)

Max Activating Token Index: 129

Text #12

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.4878. Min Act: -0.1684

Data Index: 8153980 (Open Web Text)

Max Activating Token Index: 98

Text #13

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.4879. Min Act: -0.1622

Data Index: 6580759 (Open Web Text)

Max Activating Token Index: 247

Text #14

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.4875. Min Act: -0.1673

Data Index: 6030519 (Open Web Text)

Max Activating Token Index: 61

Text #15

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.4793. Min Act: -0.1696

Data Index: 6903301 (Open Web Text)

Max Activating Token Index: 301

Text #16

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.4760. Min Act: -0.1699

Data Index: 1540396 (Open Web Text)

Max Activating Token Index: 163

Text #17

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.4794. Min Act: -0.1698

Data Index: 3446063 (Open Web Text)

Max Activating Token Index: 277

Text #18

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.4708. Min Act: -0.1700

Data Index: 5619934 (Open Web Text)

Max Activating Token Index: 253

Text #19

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.4768. Min Act: -0.1643

Data Index: 2112569 (Open Web Text)

Max Activating Token Index: 227