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

Dataset: Open Web Text

Neuron 1234 in Layer 2

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: 4.0347. Min Range: -4.0347

Max Act: 4.0347. Min Act: -0.1700

Data Index: 1002761 (Open Web Text)

Max Activating Token Index: 994

Text #1

Max Range: 4.0347. Min Range: -4.0347

Max Act: 3.9915. Min Act: -0.1700

Data Index: 8051037 (Open Web Text)

Max Activating Token Index: 402

Text #2

Max Range: 4.0347. Min Range: -4.0347

Max Act: 3.9732. Min Act: -0.1700

Data Index: 8598653 (Open Web Text)

Max Activating Token Index: 10

Text #3

Max Range: 4.0347. Min Range: -4.0347

Max Act: 3.9542. Min Act: -0.1700

Data Index: 494443 (Open Web Text)

Max Activating Token Index: 551

Text #4

Max Range: 4.0347. Min Range: -4.0347

Max Act: 3.8982. Min Act: -0.1700

Data Index: 5448339 (Open Web Text)

Max Activating Token Index: 410

Text #5

Max Range: 4.0347. Min Range: -4.0347

Max Act: 3.9376. Min Act: -0.1700

Data Index: 6410751 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 4.0347. Min Range: -4.0347

Max Act: 3.9154. Min Act: -0.1700

Data Index: 4644617 (Open Web Text)

Max Activating Token Index: 980

Text #7

Max Range: 4.0347. Min Range: -4.0347

Max Act: 3.9253. Min Act: -0.1700

Data Index: 7823184 (Open Web Text)

Max Activating Token Index: 468

Text #8

Max Range: 4.0347. Min Range: -4.0347

Max Act: 3.9131. Min Act: -0.1700

Data Index: 4442841 (Open Web Text)

Max Activating Token Index: 451

Text #9

Max Range: 4.0347. Min Range: -4.0347

Max Act: 3.9147. Min Act: -0.1700

Data Index: 4455128 (Open Web Text)

Max Activating Token Index: 289

Text #10

Max Range: 4.0347. Min Range: -4.0347

Max Act: 3.9116. Min Act: -0.1700

Data Index: 4213206 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 4.0347. Min Range: -4.0347

Max Act: 3.9031. Min Act: -0.1700

Data Index: 634588 (Open Web Text)

Max Activating Token Index: 446

Text #12

Max Range: 4.0347. Min Range: -4.0347

Max Act: 3.8674. Min Act: -0.1700

Data Index: 7827057 (Open Web Text)

Max Activating Token Index: 790

Text #13

Max Range: 4.0347. Min Range: -4.0347

Max Act: 3.8969. Min Act: -0.1700

Data Index: 5019155 (Open Web Text)

Max Activating Token Index: 134

Text #14

Max Range: 4.0347. Min Range: -4.0347

Max Act: 3.8826. Min Act: -0.1700

Data Index: 3951596 (Open Web Text)

Max Activating Token Index: 279

Text #15

Max Range: 4.0347. Min Range: -4.0347

Max Act: 3.8956. Min Act: -0.1700

Data Index: 6249863 (Open Web Text)

Max Activating Token Index: 615

Text #16

Max Range: 4.0347. Min Range: -4.0347

Max Act: 3.9084. Min Act: -0.1700

Data Index: 887248 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 4.0347. Min Range: -4.0347

Max Act: 3.8717. Min Act: -0.1700

Data Index: 5900188 (Open Web Text)

Max Activating Token Index: 239

Text #18

Max Range: 4.0347. Min Range: -4.0347

Max Act: 3.8712. Min Act: -0.1700

Data Index: 3791647 (Open Web Text)

Max Activating Token Index: 191

Text #19

Max Range: 4.0347. Min Range: -4.0347

Max Act: 3.8985. Min Act: -0.1700

Data Index: 2833583 (Open Web Text)

Max Activating Token Index: 664