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

Dataset: Open Web Text

Neuron 670 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: 4.7365. Min Range: -4.7365

Max Act: 4.7365. Min Act: -0.1700

Data Index: 1798262 (Open Web Text)

Max Activating Token Index: 773

Text #1

Max Range: 4.7365. Min Range: -4.7365

Max Act: 4.5859. Min Act: -0.1700

Data Index: 5639578 (Open Web Text)

Max Activating Token Index: 239

Text #2

Max Range: 4.7365. Min Range: -4.7365

Max Act: 4.6002. Min Act: -0.1700

Data Index: 6555186 (Open Web Text)

Max Activating Token Index: 987

Text #3

Max Range: 4.7365. Min Range: -4.7365

Max Act: 4.5892. Min Act: -0.1700

Data Index: 8613135 (Open Web Text)

Max Activating Token Index: 325

Text #4

Max Range: 4.7365. Min Range: -4.7365

Max Act: 4.6140. Min Act: -0.1700

Data Index: 7983992 (Open Web Text)

Max Activating Token Index: 586

Text #5

Max Range: 4.7365. Min Range: -4.7365

Max Act: 4.5515. Min Act: -0.1700

Data Index: 8802264 (Open Web Text)

Max Activating Token Index: 938

Text #6

Max Range: 4.7365. Min Range: -4.7365

Max Act: 4.5394. Min Act: -0.1700

Data Index: 7256339 (Open Web Text)

Max Activating Token Index: 218

Text #7

Max Range: 4.7365. Min Range: -4.7365

Max Act: 4.5472. Min Act: -0.1700

Data Index: 1258601 (Open Web Text)

Max Activating Token Index: 903

Text #8

Max Range: 4.7365. Min Range: -4.7365

Max Act: 4.4979. Min Act: -0.1700

Data Index: 4883024 (Open Web Text)

Max Activating Token Index: 253

Text #9

Max Range: 4.7365. Min Range: -4.7365

Max Act: 4.5262. Min Act: -0.1700

Data Index: 3624031 (Open Web Text)

Max Activating Token Index: 609

Text #10

Max Range: 4.7365. Min Range: -4.7365

Max Act: 4.5233. Min Act: -0.1700

Data Index: 1936811 (Open Web Text)

Max Activating Token Index: 465

Text #11

Max Range: 4.7365. Min Range: -4.7365

Max Act: 4.4790. Min Act: -0.1700

Data Index: 572435 (Open Web Text)

Max Activating Token Index: 825

Text #12

Max Range: 4.7365. Min Range: -4.7365

Max Act: 4.4905. Min Act: -0.1700

Data Index: 2231973 (Open Web Text)

Max Activating Token Index: 719

Text #13

Max Range: 4.7365. Min Range: -4.7365

Max Act: 4.5418. Min Act: -0.1700

Data Index: 3351265 (Open Web Text)

Max Activating Token Index: 291

Text #14

Max Range: 4.7365. Min Range: -4.7365

Max Act: 4.4565. Min Act: -0.1700

Data Index: 8127315 (Open Web Text)

Max Activating Token Index: 172

Text #15

Max Range: 4.7365. Min Range: -4.7365

Max Act: 4.4593. Min Act: -0.1700

Data Index: 3832180 (Open Web Text)

Max Activating Token Index: 849

Text #16

Max Range: 4.7365. Min Range: -4.7365

Max Act: 4.4578. Min Act: -0.1700

Data Index: 3780457 (Open Web Text)

Max Activating Token Index: 870

Text #17

Max Range: 4.7365. Min Range: -4.7365

Max Act: 4.4451. Min Act: -0.1700

Data Index: 6471959 (Open Web Text)

Max Activating Token Index: 755

Text #18

Max Range: 4.7365. Min Range: -4.7365

Max Act: 4.4217. Min Act: -0.1700

Data Index: 1428954 (Open Web Text)

Max Activating Token Index: 356

Text #19

Max Range: 4.7365. Min Range: -4.7365

Max Act: 4.4242. Min Act: -0.1700

Data Index: 8053225 (Open Web Text)

Max Activating Token Index: 586