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

Dataset: Open Web Text

Neuron 1111 in Layer 6

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: 6.7709. Min Range: -6.7709

Max Act: 6.7709. Min Act: -0.1700

Data Index: 6895817 (Open Web Text)

Max Activating Token Index: 23

Text #1

Max Range: 6.7709. Min Range: -6.7709

Max Act: 6.5388. Min Act: -0.1700

Data Index: 2097497 (Open Web Text)

Max Activating Token Index: 540

Text #2

Max Range: 6.7709. Min Range: -6.7709

Max Act: 6.6105. Min Act: -0.1700

Data Index: 7832459 (Open Web Text)

Max Activating Token Index: 368

Text #3

Max Range: 6.7709. Min Range: -6.7709

Max Act: 6.5623. Min Act: -0.1700

Data Index: 5219507 (Open Web Text)

Max Activating Token Index: 245

Text #4

Max Range: 6.7709. Min Range: -6.7709

Max Act: 6.5099. Min Act: -0.1700

Data Index: 283096 (Open Web Text)

Max Activating Token Index: 363

Text #5

Max Range: 6.7709. Min Range: -6.7709

Max Act: 6.5041. Min Act: -0.1700

Data Index: 4331596 (Open Web Text)

Max Activating Token Index: 50

Text #6

Max Range: 6.7709. Min Range: -6.7709

Max Act: 6.5159. Min Act: -0.1700

Data Index: 4522186 (Open Web Text)

Max Activating Token Index: 302

Text #7

Max Range: 6.7709. Min Range: -6.7709

Max Act: 6.4694. Min Act: -0.1700

Data Index: 7356272 (Open Web Text)

Max Activating Token Index: 451

Text #8

Max Range: 6.7709. Min Range: -6.7709

Max Act: 6.4915. Min Act: -0.1700

Data Index: 5072698 (Open Web Text)

Max Activating Token Index: 929

Text #9

Max Range: 6.7709. Min Range: -6.7709

Max Act: 6.4346. Min Act: -0.1700

Data Index: 229799 (Open Web Text)

Max Activating Token Index: 95

Text #10

Max Range: 6.7709. Min Range: -6.7709

Max Act: 6.3298. Min Act: -0.1700

Data Index: 5685901 (Open Web Text)

Max Activating Token Index: 177

Text #11

Max Range: 6.7709. Min Range: -6.7709

Max Act: 6.4174. Min Act: -0.1700

Data Index: 4751267 (Open Web Text)

Max Activating Token Index: 673

Text #12

Max Range: 6.7709. Min Range: -6.7709

Max Act: 6.3934. Min Act: -0.1700

Data Index: 8683126 (Open Web Text)

Max Activating Token Index: 818

Text #13

Max Range: 6.7709. Min Range: -6.7709

Max Act: 6.4059. Min Act: -0.1700

Data Index: 6008053 (Open Web Text)

Max Activating Token Index: 260

Text #14

Max Range: 6.7709. Min Range: -6.7709

Max Act: 6.4028. Min Act: -0.1700

Data Index: 1024888 (Open Web Text)

Max Activating Token Index: 717

Text #15

Max Range: 6.7709. Min Range: -6.7709

Max Act: 6.4056. Min Act: -0.1700

Data Index: 8758927 (Open Web Text)

Max Activating Token Index: 685

Text #16

Max Range: 6.7709. Min Range: -6.7709

Max Act: 6.3654. Min Act: -0.1700

Data Index: 1896474 (Open Web Text)

Max Activating Token Index: 411

Text #17

Max Range: 6.7709. Min Range: -6.7709

Max Act: 6.3870. Min Act: -0.1700

Data Index: 5096046 (Open Web Text)

Max Activating Token Index: 840

Text #18

Max Range: 6.7709. Min Range: -6.7709

Max Act: 6.3986. Min Act: -0.1700

Data Index: 6348795 (Open Web Text)

Max Activating Token Index: 480

Text #19

Max Range: 6.7709. Min Range: -6.7709

Max Act: 6.3599. Min Act: -0.1700

Data Index: 5129004 (Open Web Text)

Max Activating Token Index: 1000