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

Dataset: Open Web Text

Neuron 1606 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: 1.2986. Min Range: -1.2986

Max Act: 1.2986. Min Act: -0.1695

Data Index: 2681319 (Open Web Text)

Max Activating Token Index: 638

Text #1

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.2494. Min Act: -0.1697

Data Index: 7374057 (Open Web Text)

Max Activating Token Index: 110

Text #2

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.2515. Min Act: -0.1681

Data Index: 3467270 (Open Web Text)

Max Activating Token Index: 100

Text #3

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.2536. Min Act: -0.1695

Data Index: 231025 (Open Web Text)

Max Activating Token Index: 133

Text #4

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.2445. Min Act: -0.1700

Data Index: 6796157 (Open Web Text)

Max Activating Token Index: 94

Text #5

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.2413. Min Act: -0.1696

Data Index: 8191937 (Open Web Text)

Max Activating Token Index: 76

Text #6

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.2288. Min Act: -0.1669

Data Index: 1585775 (Open Web Text)

Max Activating Token Index: 218

Text #7

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.2237. Min Act: -0.1682

Data Index: 1600641 (Open Web Text)

Max Activating Token Index: 607

Text #8

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.2175. Min Act: -0.1617

Data Index: 1934870 (Open Web Text)

Max Activating Token Index: 172

Text #9

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.2154. Min Act: -0.1688

Data Index: 4881507 (Open Web Text)

Max Activating Token Index: 176

Text #10

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.2084. Min Act: -0.1689

Data Index: 1105161 (Open Web Text)

Max Activating Token Index: 70

Text #11

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.2146. Min Act: -0.1700

Data Index: 4527495 (Open Web Text)

Max Activating Token Index: 169

Text #12

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.2157. Min Act: -0.1699

Data Index: 6573647 (Open Web Text)

Max Activating Token Index: 127

Text #13

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.2037. Min Act: -0.1698

Data Index: 3902228 (Open Web Text)

Max Activating Token Index: 96

Text #14

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.2090. Min Act: -0.1693

Data Index: 866098 (Open Web Text)

Max Activating Token Index: 106

Text #15

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.2053. Min Act: -0.1650

Data Index: 3686511 (Open Web Text)

Max Activating Token Index: 130

Text #16

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.2032. Min Act: -0.1700

Data Index: 6921177 (Open Web Text)

Max Activating Token Index: 461

Text #17

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.2093. Min Act: -0.1691

Data Index: 1648218 (Open Web Text)

Max Activating Token Index: 592

Text #18

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.1976. Min Act: -0.1691

Data Index: 4223709 (Open Web Text)

Max Activating Token Index: 896

Text #19

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.2024. Min Act: -0.1694

Data Index: 6136503 (Open Web Text)

Max Activating Token Index: 908