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

Dataset: Open Web Text

Neuron 137 in Layer 5

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: 4.9240. Min Range: -4.9240

Max Act: 4.9015. Min Act: -0.1700

Data Index: 1362782 (Open Web Text)

Max Activating Token Index: 827

Text #1

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.9240. Min Act: -0.1700

Data Index: 6560914 (Open Web Text)

Max Activating Token Index: 56

Text #2

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.8891. Min Act: -0.1700

Data Index: 5418385 (Open Web Text)

Max Activating Token Index: 672

Text #3

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.7585. Min Act: -0.1700

Data Index: 2990735 (Open Web Text)

Max Activating Token Index: 126

Text #4

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.5823. Min Act: -0.1700

Data Index: 2348340 (Open Web Text)

Max Activating Token Index: 394

Text #5

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.5879. Min Act: -0.1700

Data Index: 852618 (Open Web Text)

Max Activating Token Index: 360

Text #6

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.6111. Min Act: -0.1700

Data Index: 1581515 (Open Web Text)

Max Activating Token Index: 431

Text #7

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.5390. Min Act: -0.1700

Data Index: 4306490 (Open Web Text)

Max Activating Token Index: 101

Text #8

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.5180. Min Act: -0.1700

Data Index: 2701074 (Open Web Text)

Max Activating Token Index: 68

Text #9

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.4923. Min Act: -0.1700

Data Index: 2541591 (Open Web Text)

Max Activating Token Index: 109

Text #10

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.4742. Min Act: -0.1700

Data Index: 1268547 (Open Web Text)

Max Activating Token Index: 329

Text #11

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.4330. Min Act: -0.1700

Data Index: 7674536 (Open Web Text)

Max Activating Token Index: 282

Text #12

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.4397. Min Act: -0.1700

Data Index: 3980774 (Open Web Text)

Max Activating Token Index: 54

Text #13

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.4720. Min Act: -0.1700

Data Index: 4320290 (Open Web Text)

Max Activating Token Index: 620

Text #14

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.4358. Min Act: -0.1700

Data Index: 3611251 (Open Web Text)

Max Activating Token Index: 472

Text #15

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.4327. Min Act: -0.1700

Data Index: 1412014 (Open Web Text)

Max Activating Token Index: 531

Text #16

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.4184. Min Act: -0.1700

Data Index: 7798516 (Open Web Text)

Max Activating Token Index: 862

Text #17

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.4032. Min Act: -0.1700

Data Index: 5628449 (Open Web Text)

Max Activating Token Index: 105

Text #18

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.4005. Min Act: -0.1700

Data Index: 1261424 (Open Web Text)

Max Activating Token Index: 1014

Text #19

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.3707. Min Act: -0.1700

Data Index: 2514152 (Open Web Text)

Max Activating Token Index: 430