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

Dataset: Open Web Text

Neuron 2528 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: 1.7994. Min Range: -1.7994

Max Act: 1.7994. Min Act: -0.1700

Data Index: 6470852 (Open Web Text)

Max Activating Token Index: 342

Text #1

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.7958. Min Act: -0.1700

Data Index: 6470851 (Open Web Text)

Max Activating Token Index: 739

Text #2

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.7930. Min Act: -0.1700

Data Index: 8763829 (Open Web Text)

Max Activating Token Index: 550

Text #3

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.7659. Min Act: -0.1700

Data Index: 8242166 (Open Web Text)

Max Activating Token Index: 673

Text #4

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.7610. Min Act: -0.1700

Data Index: 8461299 (Open Web Text)

Max Activating Token Index: 787

Text #5

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.7658. Min Act: -0.1700

Data Index: 4141026 (Open Web Text)

Max Activating Token Index: 551

Text #6

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.7548. Min Act: -0.1700

Data Index: 8537196 (Open Web Text)

Max Activating Token Index: 742

Text #7

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.7465. Min Act: -0.1700

Data Index: 6108983 (Open Web Text)

Max Activating Token Index: 508

Text #8

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.7442. Min Act: -0.1700

Data Index: 1429596 (Open Web Text)

Max Activating Token Index: 285

Text #9

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.7362. Min Act: -0.1700

Data Index: 4152877 (Open Web Text)

Max Activating Token Index: 429

Text #10

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.7597. Min Act: -0.1700

Data Index: 3913391 (Open Web Text)

Max Activating Token Index: 585

Text #11

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.7327. Min Act: -0.1700

Data Index: 8244646 (Open Web Text)

Max Activating Token Index: 930

Text #12

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.7287. Min Act: -0.1700

Data Index: 5878190 (Open Web Text)

Max Activating Token Index: 552

Text #13

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.7216. Min Act: -0.1700

Data Index: 5890987 (Open Web Text)

Max Activating Token Index: 885

Text #14

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.7254. Min Act: -0.1700

Data Index: 4141029 (Open Web Text)

Max Activating Token Index: 514

Text #15

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.7205. Min Act: -0.1700

Data Index: 1604664 (Open Web Text)

Max Activating Token Index: 603

Text #16

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.7321. Min Act: -0.1700

Data Index: 3455348 (Open Web Text)

Max Activating Token Index: 872

Text #17

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.7116. Min Act: -0.1700

Data Index: 2254867 (Open Web Text)

Max Activating Token Index: 205

Text #18

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.7155. Min Act: -0.1700

Data Index: 199874 (Open Web Text)

Max Activating Token Index: 433

Text #19

Max Range: 1.7994. Min Range: -1.7994

Max Act: 1.7084. Min Act: -0.1700

Data Index: 4141028 (Open Web Text)

Max Activating Token Index: 49