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

Dataset: Open Web Text

Neuron 1662 in Layer 4

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: 4.0935. Min Range: -4.0935

Max Act: 4.0935. Min Act: -0.1700

Data Index: 5027390 (Open Web Text)

Max Activating Token Index: 124

Text #1

Max Range: 4.0935. Min Range: -4.0935

Max Act: 3.7773. Min Act: -0.1700

Data Index: 1303372 (Open Web Text)

Max Activating Token Index: 540

Text #2

Max Range: 4.0935. Min Range: -4.0935

Max Act: 3.7598. Min Act: -0.1700

Data Index: 4358500 (Open Web Text)

Max Activating Token Index: 974

Text #3

Max Range: 4.0935. Min Range: -4.0935

Max Act: 3.7519. Min Act: -0.1700

Data Index: 294235 (Open Web Text)

Max Activating Token Index: 431

Text #4

Max Range: 4.0935. Min Range: -4.0935

Max Act: 3.7052. Min Act: -0.1700

Data Index: 4985941 (Open Web Text)

Max Activating Token Index: 845

Text #5

Max Range: 4.0935. Min Range: -4.0935

Max Act: 3.7203. Min Act: -0.1700

Data Index: 6652464 (Open Web Text)

Max Activating Token Index: 191

Text #6

Max Range: 4.0935. Min Range: -4.0935

Max Act: 3.6742. Min Act: -0.1700

Data Index: 8120646 (Open Web Text)

Max Activating Token Index: 587

Text #7

Max Range: 4.0935. Min Range: -4.0935

Max Act: 3.6539. Min Act: -0.1700

Data Index: 6602547 (Open Web Text)

Max Activating Token Index: 638

Text #8

Max Range: 4.0935. Min Range: -4.0935

Max Act: 3.6467. Min Act: -0.1700

Data Index: 1653964 (Open Web Text)

Max Activating Token Index: 361

Text #9

Max Range: 4.0935. Min Range: -4.0935

Max Act: 3.6316. Min Act: -0.1700

Data Index: 2615171 (Open Web Text)

Max Activating Token Index: 919

Text #10

Max Range: 4.0935. Min Range: -4.0935

Max Act: 3.6321. Min Act: -0.1700

Data Index: 7340390 (Open Web Text)

Max Activating Token Index: 137

Text #11

Max Range: 4.0935. Min Range: -4.0935

Max Act: 3.6357. Min Act: -0.1700

Data Index: 3401860 (Open Web Text)

Max Activating Token Index: 474

Text #12

Max Range: 4.0935. Min Range: -4.0935

Max Act: 3.6239. Min Act: -0.1700

Data Index: 1722191 (Open Web Text)

Max Activating Token Index: 513

Text #13

Max Range: 4.0935. Min Range: -4.0935

Max Act: 3.6469. Min Act: -0.1700

Data Index: 677201 (Open Web Text)

Max Activating Token Index: 412

Text #14

Max Range: 4.0935. Min Range: -4.0935

Max Act: 3.6284. Min Act: -0.1700

Data Index: 8328861 (Open Web Text)

Max Activating Token Index: 70

Text #15

Max Range: 4.0935. Min Range: -4.0935

Max Act: 3.6326. Min Act: -0.1700

Data Index: 2674657 (Open Web Text)

Max Activating Token Index: 784

Text #16

Max Range: 4.0935. Min Range: -4.0935

Max Act: 3.6353. Min Act: -0.1700

Data Index: 6526625 (Open Web Text)

Max Activating Token Index: 386

Text #17

Max Range: 4.0935. Min Range: -4.0935

Max Act: 3.6462. Min Act: -0.1700

Data Index: 647516 (Open Web Text)

Max Activating Token Index: 57

Text #18

Max Range: 4.0935. Min Range: -4.0935

Max Act: 3.6281. Min Act: -0.1700

Data Index: 7305448 (Open Web Text)

Max Activating Token Index: 290

Text #19

Max Range: 4.0935. Min Range: -4.0935

Max Act: 3.6432. Min Act: -0.1700

Data Index: 1997300 (Open Web Text)

Max Activating Token Index: 558