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

Dataset: Open Web Text

Neuron 276 in Layer 6

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: 4.4098. Min Range: -4.4098

Max Act: 4.4098. Min Act: -0.1700

Data Index: 6370620 (Open Web Text)

Max Activating Token Index: 819

Text #1

Max Range: 4.4098. Min Range: -4.4098

Max Act: 4.3024. Min Act: -0.1700

Data Index: 8641880 (Open Web Text)

Max Activating Token Index: 293

Text #2

Max Range: 4.4098. Min Range: -4.4098

Max Act: 4.3019. Min Act: -0.1700

Data Index: 4560925 (Open Web Text)

Max Activating Token Index: 416

Text #3

Max Range: 4.4098. Min Range: -4.4098

Max Act: 4.3115. Min Act: -0.1700

Data Index: 2377456 (Open Web Text)

Max Activating Token Index: 903

Text #4

Max Range: 4.4098. Min Range: -4.4098

Max Act: 4.2721. Min Act: -0.1700

Data Index: 5098781 (Open Web Text)

Max Activating Token Index: 466

Text #5

Max Range: 4.4098. Min Range: -4.4098

Max Act: 4.2655. Min Act: -0.1700

Data Index: 3863583 (Open Web Text)

Max Activating Token Index: 932

Text #6

Max Range: 4.4098. Min Range: -4.4098

Max Act: 4.2674. Min Act: -0.1700

Data Index: 14331 (Open Web Text)

Max Activating Token Index: 768

Text #7

Max Range: 4.4098. Min Range: -4.4098

Max Act: 4.2248. Min Act: -0.1700

Data Index: 1348395 (Open Web Text)

Max Activating Token Index: 909

Text #8

Max Range: 4.4098. Min Range: -4.4098

Max Act: 4.2327. Min Act: -0.1700

Data Index: 8648253 (Open Web Text)

Max Activating Token Index: 511

Text #9

Max Range: 4.4098. Min Range: -4.4098

Max Act: 4.2298. Min Act: -0.1700

Data Index: 1310367 (Open Web Text)

Max Activating Token Index: 71

Text #10

Max Range: 4.4098. Min Range: -4.4098

Max Act: 4.2300. Min Act: -0.1700

Data Index: 2081185 (Open Web Text)

Max Activating Token Index: 117

Text #11

Max Range: 4.4098. Min Range: -4.4098

Max Act: 4.2349. Min Act: -0.1700

Data Index: 5403292 (Open Web Text)

Max Activating Token Index: 963

Text #12

Max Range: 4.4098. Min Range: -4.4098

Max Act: 4.2273. Min Act: -0.1700

Data Index: 447971 (Open Web Text)

Max Activating Token Index: 236

Text #13

Max Range: 4.4098. Min Range: -4.4098

Max Act: 4.1938. Min Act: -0.1700

Data Index: 5686730 (Open Web Text)

Max Activating Token Index: 189

Text #14

Max Range: 4.4098. Min Range: -4.4098

Max Act: 4.2008. Min Act: -0.1700

Data Index: 3592061 (Open Web Text)

Max Activating Token Index: 367

Text #15

Max Range: 4.4098. Min Range: -4.4098

Max Act: 4.2241. Min Act: -0.1700

Data Index: 4074114 (Open Web Text)

Max Activating Token Index: 703

Text #16

Max Range: 4.4098. Min Range: -4.4098

Max Act: 4.1911. Min Act: -0.1700

Data Index: 1114584 (Open Web Text)

Max Activating Token Index: 954

Text #17

Max Range: 4.4098. Min Range: -4.4098

Max Act: 4.1917. Min Act: -0.1700

Data Index: 1565173 (Open Web Text)

Max Activating Token Index: 863

Text #18

Max Range: 4.4098. Min Range: -4.4098

Max Act: 4.2163. Min Act: -0.1700

Data Index: 3361505 (Open Web Text)

Max Activating Token Index: 759

Text #19

Max Range: 4.4098. Min Range: -4.4098

Max Act: 4.2187. Min Act: -0.1700

Data Index: 5015435 (Open Web Text)

Max Activating Token Index: 153