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

Dataset: Open Web Text

Neuron 383 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: 5.4522. Min Range: -5.4522

Max Act: 5.4522. Min Act: -0.1700

Data Index: 2600647 (Open Web Text)

Max Activating Token Index: 789

Text #1

Max Range: 5.4522. Min Range: -5.4522

Max Act: 5.3438. Min Act: -0.1700

Data Index: 4200289 (Open Web Text)

Max Activating Token Index: 584

Text #2

Max Range: 5.4522. Min Range: -5.4522

Max Act: 5.1949. Min Act: -0.1700

Data Index: 2357910 (Open Web Text)

Max Activating Token Index: 287

Text #3

Max Range: 5.4522. Min Range: -5.4522

Max Act: 5.1588. Min Act: -0.1700

Data Index: 8014789 (Open Web Text)

Max Activating Token Index: 707

Text #4

Max Range: 5.4522. Min Range: -5.4522

Max Act: 5.1591. Min Act: -0.1700

Data Index: 7849350 (Open Web Text)

Max Activating Token Index: 738

Text #5

Max Range: 5.4522. Min Range: -5.4522

Max Act: 5.1427. Min Act: -0.1700

Data Index: 7028110 (Open Web Text)

Max Activating Token Index: 212

Text #6

Max Range: 5.4522. Min Range: -5.4522

Max Act: 5.1488. Min Act: -0.1700

Data Index: 5647906 (Open Web Text)

Max Activating Token Index: 248

Text #7

Max Range: 5.4522. Min Range: -5.4522

Max Act: 5.1324. Min Act: -0.1700

Data Index: 6013021 (Open Web Text)

Max Activating Token Index: 164

Text #8

Max Range: 5.4522. Min Range: -5.4522

Max Act: 5.1111. Min Act: -0.1700

Data Index: 7875302 (Open Web Text)

Max Activating Token Index: 475

Text #9

Max Range: 5.4522. Min Range: -5.4522

Max Act: 5.0833. Min Act: -0.1700

Data Index: 7283376 (Open Web Text)

Max Activating Token Index: 382

Text #10

Max Range: 5.4522. Min Range: -5.4522

Max Act: 5.1054. Min Act: -0.1700

Data Index: 6774975 (Open Web Text)

Max Activating Token Index: 684

Text #11

Max Range: 5.4522. Min Range: -5.4522

Max Act: 5.0886. Min Act: -0.1700

Data Index: 529281 (Open Web Text)

Max Activating Token Index: 945

Text #12

Max Range: 5.4522. Min Range: -5.4522

Max Act: 5.0796. Min Act: -0.1700

Data Index: 5742257 (Open Web Text)

Max Activating Token Index: 285

Text #13

Max Range: 5.4522. Min Range: -5.4522

Max Act: 5.0825. Min Act: -0.1700

Data Index: 1938723 (Open Web Text)

Max Activating Token Index: 106

Text #14

Max Range: 5.4522. Min Range: -5.4522

Max Act: 5.1087. Min Act: -0.1700

Data Index: 5663846 (Open Web Text)

Max Activating Token Index: 207

Text #15

Max Range: 5.4522. Min Range: -5.4522

Max Act: 5.1106. Min Act: -0.1700

Data Index: 7515067 (Open Web Text)

Max Activating Token Index: 115

Text #16

Max Range: 5.4522. Min Range: -5.4522

Max Act: 5.0635. Min Act: -0.1700

Data Index: 3540240 (Open Web Text)

Max Activating Token Index: 430

Text #17

Max Range: 5.4522. Min Range: -5.4522

Max Act: 5.0708. Min Act: -0.1700

Data Index: 7644333 (Open Web Text)

Max Activating Token Index: 686

Text #18

Max Range: 5.4522. Min Range: -5.4522

Max Act: 5.0427. Min Act: -0.1700

Data Index: 373073 (Open Web Text)

Max Activating Token Index: 490

Text #19

Max Range: 5.4522. Min Range: -5.4522

Max Act: 5.0221. Min Act: -0.1700

Data Index: 1510788 (Open Web Text)

Max Activating Token Index: 372