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

Dataset: Open Web Text

Neuron 1904 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: 4.1576. Min Range: -4.1576

Max Act: 4.1576. Min Act: -0.1700

Data Index: 3402548 (Open Web Text)

Max Activating Token Index: 1007

Text #1

Max Range: 4.1576. Min Range: -4.1576

Max Act: 4.1488. Min Act: -0.1700

Data Index: 7650713 (Open Web Text)

Max Activating Token Index: 422

Text #2

Max Range: 4.1576. Min Range: -4.1576

Max Act: 4.1143. Min Act: -0.1700

Data Index: 6799916 (Open Web Text)

Max Activating Token Index: 538

Text #3

Max Range: 4.1576. Min Range: -4.1576

Max Act: 4.0849. Min Act: -0.1700

Data Index: 7233217 (Open Web Text)

Max Activating Token Index: 425

Text #4

Max Range: 4.1576. Min Range: -4.1576

Max Act: 4.0838. Min Act: -0.1700

Data Index: 4669227 (Open Web Text)

Max Activating Token Index: 191

Text #5

Max Range: 4.1576. Min Range: -4.1576

Max Act: 4.0655. Min Act: -0.1700

Data Index: 8497202 (Open Web Text)

Max Activating Token Index: 70

Text #6

Max Range: 4.1576. Min Range: -4.1576

Max Act: 4.0578. Min Act: -0.1700

Data Index: 8492091 (Open Web Text)

Max Activating Token Index: 424

Text #7

Max Range: 4.1576. Min Range: -4.1576

Max Act: 4.0794. Min Act: -0.1700

Data Index: 4576607 (Open Web Text)

Max Activating Token Index: 374

Text #8

Max Range: 4.1576. Min Range: -4.1576

Max Act: 4.0731. Min Act: -0.1700

Data Index: 1800443 (Open Web Text)

Max Activating Token Index: 20

Text #9

Max Range: 4.1576. Min Range: -4.1576

Max Act: 4.0658. Min Act: -0.1700

Data Index: 4069018 (Open Web Text)

Max Activating Token Index: 267

Text #10

Max Range: 4.1576. Min Range: -4.1576

Max Act: 4.0631. Min Act: -0.1700

Data Index: 5116195 (Open Web Text)

Max Activating Token Index: 74

Text #11

Max Range: 4.1576. Min Range: -4.1576

Max Act: 4.0233. Min Act: -0.1700

Data Index: 6095833 (Open Web Text)

Max Activating Token Index: 222

Text #12

Max Range: 4.1576. Min Range: -4.1576

Max Act: 4.0448. Min Act: -0.1700

Data Index: 6402150 (Open Web Text)

Max Activating Token Index: 20

Text #13

Max Range: 4.1576. Min Range: -4.1576

Max Act: 4.0131. Min Act: -0.1700

Data Index: 89179 (Open Web Text)

Max Activating Token Index: 457

Text #14

Max Range: 4.1576. Min Range: -4.1576

Max Act: 4.0316. Min Act: -0.1700

Data Index: 1869891 (Open Web Text)

Max Activating Token Index: 154

Text #15

Max Range: 4.1576. Min Range: -4.1576

Max Act: 4.0256. Min Act: -0.1700

Data Index: 5804868 (Open Web Text)

Max Activating Token Index: 589

Text #16

Max Range: 4.1576. Min Range: -4.1576

Max Act: 4.0432. Min Act: -0.1700

Data Index: 753733 (Open Web Text)

Max Activating Token Index: 313

Text #17

Max Range: 4.1576. Min Range: -4.1576

Max Act: 4.0275. Min Act: -0.1700

Data Index: 3234201 (Open Web Text)

Max Activating Token Index: 213

Text #18

Max Range: 4.1576. Min Range: -4.1576

Max Act: 4.0418. Min Act: -0.1700

Data Index: 5269852 (Open Web Text)

Max Activating Token Index: 636

Text #19

Max Range: 4.1576. Min Range: -4.1576

Max Act: 4.0389. Min Act: -0.1700

Data Index: 3471815 (Open Web Text)

Max Activating Token Index: 581