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

Dataset: Open Web Text

Neuron 2952 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: 3.0691. Min Range: -3.0691

Max Act: 3.0691. Min Act: -0.1700

Data Index: 7772051 (Open Web Text)

Max Activating Token Index: 1006

Text #1

Max Range: 3.0691. Min Range: -3.0691

Max Act: 3.0468. Min Act: -0.1700

Data Index: 4507959 (Open Web Text)

Max Activating Token Index: 630

Text #2

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.9920. Min Act: -0.1700

Data Index: 3218729 (Open Web Text)

Max Activating Token Index: 524

Text #3

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.9888. Min Act: -0.1700

Data Index: 7567768 (Open Web Text)

Max Activating Token Index: 612

Text #4

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.9644. Min Act: -0.1700

Data Index: 4633427 (Open Web Text)

Max Activating Token Index: 866

Text #5

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.9808. Min Act: -0.1700

Data Index: 647203 (Open Web Text)

Max Activating Token Index: 812

Text #6

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.9800. Min Act: -0.1700

Data Index: 1401062 (Open Web Text)

Max Activating Token Index: 394

Text #7

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.9757. Min Act: -0.1700

Data Index: 2964288 (Open Web Text)

Max Activating Token Index: 628

Text #8

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.9749. Min Act: -0.1700

Data Index: 7229295 (Open Web Text)

Max Activating Token Index: 802

Text #9

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.9712. Min Act: -0.1700

Data Index: 8822750 (Open Web Text)

Max Activating Token Index: 1000

Text #10

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.9545. Min Act: -0.1700

Data Index: 1334242 (Open Web Text)

Max Activating Token Index: 595

Text #11

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.9488. Min Act: -0.1700

Data Index: 978792 (Open Web Text)

Max Activating Token Index: 71

Text #12

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.9707. Min Act: -0.1700

Data Index: 4126954 (Open Web Text)

Max Activating Token Index: 432

Text #13

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.9435. Min Act: -0.1700

Data Index: 1098176 (Open Web Text)

Max Activating Token Index: 516

Text #14

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.9319. Min Act: -0.1700

Data Index: 8451129 (Open Web Text)

Max Activating Token Index: 129

Text #15

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.9408. Min Act: -0.1700

Data Index: 6567387 (Open Web Text)

Max Activating Token Index: 205

Text #16

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.9155. Min Act: -0.1700

Data Index: 3951717 (Open Web Text)

Max Activating Token Index: 944

Text #17

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.9125. Min Act: -0.1700

Data Index: 543391 (Open Web Text)

Max Activating Token Index: 279

Text #18

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.9055. Min Act: -0.1700

Data Index: 7704256 (Open Web Text)

Max Activating Token Index: 298

Text #19

Max Range: 3.0691. Min Range: -3.0691

Max Act: 2.9369. Min Act: -0.1700

Data Index: 2249044 (Open Web Text)

Max Activating Token Index: 443