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

Dataset: Open Web Text

Neuron 2337 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: 4.6052. Min Range: -4.6052

Max Act: 4.6052. Min Act: -0.1700

Data Index: 4155700 (Open Web Text)

Max Activating Token Index: 11

Text #1

Max Range: 4.6052. Min Range: -4.6052

Max Act: 4.5500. Min Act: -0.1700

Data Index: 6712971 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 4.6052. Min Range: -4.6052

Max Act: 4.4960. Min Act: -0.1700

Data Index: 8339024 (Open Web Text)

Max Activating Token Index: 119

Text #3

Max Range: 4.6052. Min Range: -4.6052

Max Act: 4.4607. Min Act: -0.1700

Data Index: 903806 (Open Web Text)

Max Activating Token Index: 655

Text #4

Max Range: 4.6052. Min Range: -4.6052

Max Act: 4.4126. Min Act: -0.1700

Data Index: 479189 (Open Web Text)

Max Activating Token Index: 722

Text #5

Max Range: 4.6052. Min Range: -4.6052

Max Act: 4.4340. Min Act: -0.1700

Data Index: 4459764 (Open Web Text)

Max Activating Token Index: 497

Text #6

Max Range: 4.6052. Min Range: -4.6052

Max Act: 4.3778. Min Act: -0.1700

Data Index: 8488861 (Open Web Text)

Max Activating Token Index: 314

Text #7

Max Range: 4.6052. Min Range: -4.6052

Max Act: 4.3803. Min Act: -0.1700

Data Index: 6739199 (Open Web Text)

Max Activating Token Index: 986

Text #8

Max Range: 4.6052. Min Range: -4.6052

Max Act: 4.3639. Min Act: -0.1700

Data Index: 2464041 (Open Web Text)

Max Activating Token Index: 894

Text #9

Max Range: 4.6052. Min Range: -4.6052

Max Act: 4.3118. Min Act: -0.1700

Data Index: 2526263 (Open Web Text)

Max Activating Token Index: 238

Text #10

Max Range: 4.6052. Min Range: -4.6052

Max Act: 4.2884. Min Act: -0.1700

Data Index: 7817143 (Open Web Text)

Max Activating Token Index: 978

Text #11

Max Range: 4.6052. Min Range: -4.6052

Max Act: 4.3070. Min Act: -0.1700

Data Index: 3811065 (Open Web Text)

Max Activating Token Index: 267

Text #12

Max Range: 4.6052. Min Range: -4.6052

Max Act: 4.3237. Min Act: -0.1700

Data Index: 7192262 (Open Web Text)

Max Activating Token Index: 27

Text #13

Max Range: 4.6052. Min Range: -4.6052

Max Act: 4.3414. Min Act: -0.1700

Data Index: 1438268 (Open Web Text)

Max Activating Token Index: 398

Text #14

Max Range: 4.6052. Min Range: -4.6052

Max Act: 4.3082. Min Act: -0.1700

Data Index: 4411256 (Open Web Text)

Max Activating Token Index: 789

Text #15

Max Range: 4.6052. Min Range: -4.6052

Max Act: 4.2862. Min Act: -0.1700

Data Index: 1175614 (Open Web Text)

Max Activating Token Index: 576

Text #16

Max Range: 4.6052. Min Range: -4.6052

Max Act: 4.2459. Min Act: -0.1700

Data Index: 27579 (Open Web Text)

Max Activating Token Index: 475

Text #17

Max Range: 4.6052. Min Range: -4.6052

Max Act: 4.2591. Min Act: -0.1700

Data Index: 5298259 (Open Web Text)

Max Activating Token Index: 520

Text #18

Max Range: 4.6052. Min Range: -4.6052

Max Act: 4.2562. Min Act: -0.1700

Data Index: 2876460 (Open Web Text)

Max Activating Token Index: 110

Text #19

Max Range: 4.6052. Min Range: -4.6052

Max Act: 4.2279. Min Act: -0.1700

Data Index: 7529317 (Open Web Text)

Max Activating Token Index: 174