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

Dataset: Open Web Text

Neuron 2078 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: 3.5037. Min Range: -3.5037

Max Act: 3.5037. Min Act: -0.1700

Data Index: 8567377 (Open Web Text)

Max Activating Token Index: 518

Text #1

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.4352. Min Act: -0.1700

Data Index: 2203565 (Open Web Text)

Max Activating Token Index: 463

Text #2

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.3263. Min Act: -0.1700

Data Index: 5017213 (Open Web Text)

Max Activating Token Index: 485

Text #3

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.3177. Min Act: -0.1700

Data Index: 3394899 (Open Web Text)

Max Activating Token Index: 41

Text #4

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.2968. Min Act: -0.1700

Data Index: 2622943 (Open Web Text)

Max Activating Token Index: 224

Text #5

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.2892. Min Act: -0.1700

Data Index: 3954747 (Open Web Text)

Max Activating Token Index: 368

Text #6

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.2728. Min Act: -0.1700

Data Index: 8636316 (Open Web Text)

Max Activating Token Index: 851

Text #7

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.2984. Min Act: -0.1700

Data Index: 7623755 (Open Web Text)

Max Activating Token Index: 217

Text #8

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.2642. Min Act: -0.1700

Data Index: 1515873 (Open Web Text)

Max Activating Token Index: 69

Text #9

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.2296. Min Act: -0.1700

Data Index: 1915051 (Open Web Text)

Max Activating Token Index: 903

Text #10

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.2689. Min Act: -0.1700

Data Index: 814259 (Open Web Text)

Max Activating Token Index: 407

Text #11

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.2326. Min Act: -0.1700

Data Index: 4129978 (Open Web Text)

Max Activating Token Index: 873

Text #12

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.2673. Min Act: -0.1700

Data Index: 343172 (Open Web Text)

Max Activating Token Index: 875

Text #13

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.2589. Min Act: -0.1700

Data Index: 8671040 (Open Web Text)

Max Activating Token Index: 320

Text #14

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.2261. Min Act: -0.1700

Data Index: 2238514 (Open Web Text)

Max Activating Token Index: 829

Text #15

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.2251. Min Act: -0.1700

Data Index: 6074762 (Open Web Text)

Max Activating Token Index: 394

Text #16

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.2365. Min Act: -0.1700

Data Index: 7273989 (Open Web Text)

Max Activating Token Index: 493

Text #17

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.2222. Min Act: -0.1700

Data Index: 1719803 (Open Web Text)

Max Activating Token Index: 228

Text #18

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.2226. Min Act: -0.1700

Data Index: 629856 (Open Web Text)

Max Activating Token Index: 1008

Text #19

Max Range: 3.5037. Min Range: -3.5037

Max Act: 3.2299. Min Act: -0.1700

Data Index: 8243301 (Open Web Text)

Max Activating Token Index: 508