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

Dataset: Open Web Text

Neuron 225 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: 3.0611. Min Range: -3.0611

Max Act: 3.0611. Min Act: -0.1700

Data Index: 7998509 (Open Web Text)

Max Activating Token Index: 52

Text #1

Max Range: 3.0611. Min Range: -3.0611

Max Act: 2.8680. Min Act: -0.1700

Data Index: 3060615 (Open Web Text)

Max Activating Token Index: 421

Text #2

Max Range: 3.0611. Min Range: -3.0611

Max Act: 2.8248. Min Act: -0.1700

Data Index: 3143052 (Open Web Text)

Max Activating Token Index: 207

Text #3

Max Range: 3.0611. Min Range: -3.0611

Max Act: 2.7955. Min Act: -0.1700

Data Index: 3148286 (Open Web Text)

Max Activating Token Index: 168

Text #4

Max Range: 3.0611. Min Range: -3.0611

Max Act: 2.7925. Min Act: -0.1700

Data Index: 5924 (Open Web Text)

Max Activating Token Index: 103

Text #5

Max Range: 3.0611. Min Range: -3.0611

Max Act: 2.7920. Min Act: -0.1692

Data Index: 6648639 (Open Web Text)

Max Activating Token Index: 27

Text #6

Max Range: 3.0611. Min Range: -3.0611

Max Act: 2.7948. Min Act: -0.1700

Data Index: 4318719 (Open Web Text)

Max Activating Token Index: 309

Text #7

Max Range: 3.0611. Min Range: -3.0611

Max Act: 2.7780. Min Act: -0.1700

Data Index: 3275694 (Open Web Text)

Max Activating Token Index: 383

Text #8

Max Range: 3.0611. Min Range: -3.0611

Max Act: 2.7847. Min Act: -0.1700

Data Index: 2789546 (Open Web Text)

Max Activating Token Index: 752

Text #9

Max Range: 3.0611. Min Range: -3.0611

Max Act: 2.7705. Min Act: -0.1700

Data Index: 6201376 (Open Web Text)

Max Activating Token Index: 285

Text #10

Max Range: 3.0611. Min Range: -3.0611

Max Act: 2.7689. Min Act: -0.1700

Data Index: 7597317 (Open Web Text)

Max Activating Token Index: 44

Text #11

Max Range: 3.0611. Min Range: -3.0611

Max Act: 2.7464. Min Act: -0.1700

Data Index: 7777960 (Open Web Text)

Max Activating Token Index: 263

Text #12

Max Range: 3.0611. Min Range: -3.0611

Max Act: 2.7069. Min Act: -0.1700

Data Index: 430815 (Open Web Text)

Max Activating Token Index: 536

Text #13

Max Range: 3.0611. Min Range: -3.0611

Max Act: 2.7557. Min Act: -0.1700

Data Index: 2628126 (Open Web Text)

Max Activating Token Index: 355

Text #14

Max Range: 3.0611. Min Range: -3.0611

Max Act: 2.7482. Min Act: -0.1700

Data Index: 704070 (Open Web Text)

Max Activating Token Index: 535

Text #15

Max Range: 3.0611. Min Range: -3.0611

Max Act: 2.7452. Min Act: -0.1700

Data Index: 6950444 (Open Web Text)

Max Activating Token Index: 284

Text #16

Max Range: 3.0611. Min Range: -3.0611

Max Act: 2.7348. Min Act: -0.1700

Data Index: 4032764 (Open Web Text)

Max Activating Token Index: 544

Text #17

Max Range: 3.0611. Min Range: -3.0611

Max Act: 2.7185. Min Act: -0.1700

Data Index: 7471940 (Open Web Text)

Max Activating Token Index: 391

Text #18

Max Range: 3.0611. Min Range: -3.0611

Max Act: 2.7329. Min Act: -0.1700

Data Index: 1374016 (Open Web Text)

Max Activating Token Index: 350

Text #19

Max Range: 3.0611. Min Range: -3.0611

Max Act: 2.7261. Min Act: -0.1700

Data Index: 146281 (Open Web Text)

Max Activating Token Index: 188