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

Dataset: Open Web Text

Neuron 810 in Layer 3

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: 1.5934. Min Range: -1.5934

Max Act: 1.5934. Min Act: -0.1700

Data Index: 2805042 (Open Web Text)

Max Activating Token Index: 366

Text #1

Max Range: 1.5934. Min Range: -1.5934

Max Act: 1.5736. Min Act: -0.1700

Data Index: 7457904 (Open Web Text)

Max Activating Token Index: 487

Text #2

Max Range: 1.5934. Min Range: -1.5934

Max Act: 1.5510. Min Act: -0.1700

Data Index: 4429965 (Open Web Text)

Max Activating Token Index: 488

Text #3

Max Range: 1.5934. Min Range: -1.5934

Max Act: 1.5524. Min Act: -0.1700

Data Index: 3046592 (Open Web Text)

Max Activating Token Index: 462

Text #4

Max Range: 1.5934. Min Range: -1.5934

Max Act: 1.5610. Min Act: -0.1700

Data Index: 44115 (Open Web Text)

Max Activating Token Index: 23

Text #5

Max Range: 1.5934. Min Range: -1.5934

Max Act: 1.5435. Min Act: -0.1699

Data Index: 6225798 (Open Web Text)

Max Activating Token Index: 430

Text #6

Max Range: 1.5934. Min Range: -1.5934

Max Act: 1.5430. Min Act: -0.1700

Data Index: 6923243 (Open Web Text)

Max Activating Token Index: 374

Text #7

Max Range: 1.5934. Min Range: -1.5934

Max Act: 1.5471. Min Act: -0.1700

Data Index: 109949 (Open Web Text)

Max Activating Token Index: 701

Text #8

Max Range: 1.5934. Min Range: -1.5934

Max Act: 1.5457. Min Act: -0.1700

Data Index: 1524758 (Open Web Text)

Max Activating Token Index: 444

Text #9

Max Range: 1.5934. Min Range: -1.5934

Max Act: 1.5506. Min Act: -0.1700

Data Index: 7933110 (Open Web Text)

Max Activating Token Index: 707

Text #10

Max Range: 1.5934. Min Range: -1.5934

Max Act: 1.5432. Min Act: -0.1700

Data Index: 43347 (Open Web Text)

Max Activating Token Index: 597

Text #11

Max Range: 1.5934. Min Range: -1.5934

Max Act: 1.5344. Min Act: -0.1700

Data Index: 1665274 (Open Web Text)

Max Activating Token Index: 16

Text #12

Max Range: 1.5934. Min Range: -1.5934

Max Act: 1.5236. Min Act: -0.1700

Data Index: 1601938 (Open Web Text)

Max Activating Token Index: 684

Text #13

Max Range: 1.5934. Min Range: -1.5934

Max Act: 1.5038. Min Act: -0.1700

Data Index: 2784137 (Open Web Text)

Max Activating Token Index: 897

Text #14

Max Range: 1.5934. Min Range: -1.5934

Max Act: 1.5308. Min Act: -0.1700

Data Index: 1147860 (Open Web Text)

Max Activating Token Index: 406

Text #15

Max Range: 1.5934. Min Range: -1.5934

Max Act: 1.5267. Min Act: -0.1700

Data Index: 1427303 (Open Web Text)

Max Activating Token Index: 161

Text #16

Max Range: 1.5934. Min Range: -1.5934

Max Act: 1.5222. Min Act: -0.1700

Data Index: 4970291 (Open Web Text)

Max Activating Token Index: 849

Text #17

Max Range: 1.5934. Min Range: -1.5934

Max Act: 1.5356. Min Act: -0.1700

Data Index: 1219181 (Open Web Text)

Max Activating Token Index: 745

Text #18

Max Range: 1.5934. Min Range: -1.5934

Max Act: 1.5010. Min Act: -0.1700

Data Index: 3749906 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 1.5934. Min Range: -1.5934

Max Act: 1.5111. Min Act: -0.1700

Data Index: 66887 (Open Web Text)

Max Activating Token Index: 714