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

Dataset: Open Web Text

Neuron 2774 in Layer 1

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: 4.8451. Min Range: -4.8451

Max Act: 4.8379. Min Act: -0.1700

Data Index: 4519725 (Open Web Text)

Max Activating Token Index: 651

Text #1

Max Range: 4.8451. Min Range: -4.8451

Max Act: 4.8281. Min Act: -0.1700

Data Index: 1259502 (Open Web Text)

Max Activating Token Index: 874

Text #2

Max Range: 4.8451. Min Range: -4.8451

Max Act: 4.8225. Min Act: -0.1700

Data Index: 77085 (Open Web Text)

Max Activating Token Index: 77

Text #3

Max Range: 4.8451. Min Range: -4.8451

Max Act: 4.8339. Min Act: -0.1700

Data Index: 7370297 (Open Web Text)

Max Activating Token Index: 304

Text #4

Max Range: 4.8451. Min Range: -4.8451

Max Act: 4.8451. Min Act: -0.1700

Data Index: 4217201 (Open Web Text)

Max Activating Token Index: 462

Text #5

Max Range: 4.8451. Min Range: -4.8451

Max Act: 4.7826. Min Act: -0.1700

Data Index: 1356163 (Open Web Text)

Max Activating Token Index: 930

Text #6

Max Range: 4.8451. Min Range: -4.8451

Max Act: 4.8088. Min Act: -0.1700

Data Index: 7798439 (Open Web Text)

Max Activating Token Index: 230

Text #7

Max Range: 4.8451. Min Range: -4.8451

Max Act: 4.8114. Min Act: -0.1700

Data Index: 4199098 (Open Web Text)

Max Activating Token Index: 222

Text #8

Max Range: 4.8451. Min Range: -4.8451

Max Act: 4.8009. Min Act: -0.1700

Data Index: 1027388 (Open Web Text)

Max Activating Token Index: 290

Text #9

Max Range: 4.8451. Min Range: -4.8451

Max Act: 4.7718. Min Act: -0.1700

Data Index: 7209788 (Open Web Text)

Max Activating Token Index: 297

Text #10

Max Range: 4.8451. Min Range: -4.8451

Max Act: 4.7395. Min Act: -0.1700

Data Index: 4208627 (Open Web Text)

Max Activating Token Index: 670

Text #11

Max Range: 4.8451. Min Range: -4.8451

Max Act: 4.7896. Min Act: -0.1700

Data Index: 751321 (Open Web Text)

Max Activating Token Index: 345

Text #12

Max Range: 4.8451. Min Range: -4.8451

Max Act: 4.7717. Min Act: -0.1700

Data Index: 1061051 (Open Web Text)

Max Activating Token Index: 716

Text #13

Max Range: 4.8451. Min Range: -4.8451

Max Act: 4.7559. Min Act: -0.1700

Data Index: 5178044 (Open Web Text)

Max Activating Token Index: 537

Text #14

Max Range: 4.8451. Min Range: -4.8451

Max Act: 4.7334. Min Act: -0.1700

Data Index: 7154837 (Open Web Text)

Max Activating Token Index: 632

Text #15

Max Range: 4.8451. Min Range: -4.8451

Max Act: 4.7554. Min Act: -0.1700

Data Index: 8131557 (Open Web Text)

Max Activating Token Index: 802

Text #16

Max Range: 4.8451. Min Range: -4.8451

Max Act: 4.7365. Min Act: -0.1700

Data Index: 6848405 (Open Web Text)

Max Activating Token Index: 106

Text #17

Max Range: 4.8451. Min Range: -4.8451

Max Act: 4.7365. Min Act: -0.1700

Data Index: 4267023 (Open Web Text)

Max Activating Token Index: 274

Text #18

Max Range: 4.8451. Min Range: -4.8451

Max Act: 4.7280. Min Act: -0.1700

Data Index: 3683421 (Open Web Text)

Max Activating Token Index: 361

Text #19

Max Range: 4.8451. Min Range: -4.8451

Max Act: 4.7372. Min Act: -0.1700

Data Index: 8718092 (Open Web Text)

Max Activating Token Index: 227