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

Dataset: Open Web Text

Neuron 785 in Layer 4

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: 4.4433. Min Range: -4.4433

Max Act: 4.4433. Min Act: -0.1700

Data Index: 6992370 (Open Web Text)

Max Activating Token Index: 465

Text #1

Max Range: 4.4433. Min Range: -4.4433

Max Act: 4.3298. Min Act: -0.1700

Data Index: 4015303 (Open Web Text)

Max Activating Token Index: 184

Text #2

Max Range: 4.4433. Min Range: -4.4433

Max Act: 4.2913. Min Act: -0.1700

Data Index: 3247277 (Open Web Text)

Max Activating Token Index: 427

Text #3

Max Range: 4.4433. Min Range: -4.4433

Max Act: 4.2903. Min Act: -0.1700

Data Index: 1504353 (Open Web Text)

Max Activating Token Index: 662

Text #4

Max Range: 4.4433. Min Range: -4.4433

Max Act: 4.2980. Min Act: -0.1700

Data Index: 3449956 (Open Web Text)

Max Activating Token Index: 676

Text #5

Max Range: 4.4433. Min Range: -4.4433

Max Act: 4.2685. Min Act: -0.1700

Data Index: 1423747 (Open Web Text)

Max Activating Token Index: 544

Text #6

Max Range: 4.4433. Min Range: -4.4433

Max Act: 4.2752. Min Act: -0.1700

Data Index: 2954017 (Open Web Text)

Max Activating Token Index: 272

Text #7

Max Range: 4.4433. Min Range: -4.4433

Max Act: 4.2341. Min Act: -0.1700

Data Index: 2308820 (Open Web Text)

Max Activating Token Index: 568

Text #8

Max Range: 4.4433. Min Range: -4.4433

Max Act: 4.2531. Min Act: -0.1700

Data Index: 6872501 (Open Web Text)

Max Activating Token Index: 202

Text #9

Max Range: 4.4433. Min Range: -4.4433

Max Act: 4.2380. Min Act: -0.1700

Data Index: 4748679 (Open Web Text)

Max Activating Token Index: 782

Text #10

Max Range: 4.4433. Min Range: -4.4433

Max Act: 4.2361. Min Act: -0.1700

Data Index: 4765738 (Open Web Text)

Max Activating Token Index: 308

Text #11

Max Range: 4.4433. Min Range: -4.4433

Max Act: 4.2008. Min Act: -0.1700

Data Index: 6621408 (Open Web Text)

Max Activating Token Index: 976

Text #12

Max Range: 4.4433. Min Range: -4.4433

Max Act: 4.1900. Min Act: -0.1700

Data Index: 6359246 (Open Web Text)

Max Activating Token Index: 989

Text #13

Max Range: 4.4433. Min Range: -4.4433

Max Act: 4.2117. Min Act: -0.1700

Data Index: 1793187 (Open Web Text)

Max Activating Token Index: 757

Text #14

Max Range: 4.4433. Min Range: -4.4433

Max Act: 4.2276. Min Act: -0.1700

Data Index: 8640767 (Open Web Text)

Max Activating Token Index: 308

Text #15

Max Range: 4.4433. Min Range: -4.4433

Max Act: 4.2149. Min Act: -0.1700

Data Index: 6788722 (Open Web Text)

Max Activating Token Index: 422

Text #16

Max Range: 4.4433. Min Range: -4.4433

Max Act: 4.2082. Min Act: -0.1700

Data Index: 4649431 (Open Web Text)

Max Activating Token Index: 298

Text #17

Max Range: 4.4433. Min Range: -4.4433

Max Act: 4.1588. Min Act: -0.1700

Data Index: 4837521 (Open Web Text)

Max Activating Token Index: 553

Text #18

Max Range: 4.4433. Min Range: -4.4433

Max Act: 4.1941. Min Act: -0.1700

Data Index: 6287736 (Open Web Text)

Max Activating Token Index: 771

Text #19

Max Range: 4.4433. Min Range: -4.4433

Max Act: 4.2065. Min Act: -0.1700

Data Index: 4147545 (Open Web Text)

Max Activating Token Index: 949