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

Dataset: Open Web Text

Neuron 964 in Layer 0

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: 6.4938. Min Range: -6.4938

Max Act: 6.4938. Min Act: -0.1700

Data Index: 5880667 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 6.4938. Min Range: -6.4938

Max Act: 6.4661. Min Act: -0.1700

Data Index: 4667223 (Open Web Text)

Max Activating Token Index: 40

Text #2

Max Range: 6.4938. Min Range: -6.4938

Max Act: 6.4365. Min Act: -0.1700

Data Index: 3067180 (Open Web Text)

Max Activating Token Index: 249

Text #3

Max Range: 6.4938. Min Range: -6.4938

Max Act: 6.2417. Min Act: -0.1700

Data Index: 8361266 (Open Web Text)

Max Activating Token Index: 15

Text #4

Max Range: 6.4938. Min Range: -6.4938

Max Act: 6.1805. Min Act: -0.1700

Data Index: 356913 (Open Web Text)

Max Activating Token Index: 819

Text #5

Max Range: 6.4938. Min Range: -6.4938

Max Act: 6.1650. Min Act: -0.1700

Data Index: 5643170 (Open Web Text)

Max Activating Token Index: 825

Text #6

Max Range: 6.4938. Min Range: -6.4938

Max Act: 6.1314. Min Act: -0.1700

Data Index: 50627 (Open Web Text)

Max Activating Token Index: 373

Text #7

Max Range: 6.4938. Min Range: -6.4938

Max Act: 6.1101. Min Act: -0.1700

Data Index: 4929037 (Open Web Text)

Max Activating Token Index: 352

Text #8

Max Range: 6.4938. Min Range: -6.4938

Max Act: 6.0641. Min Act: -0.1700

Data Index: 2064520 (Open Web Text)

Max Activating Token Index: 614

Text #9

Max Range: 6.4938. Min Range: -6.4938

Max Act: 6.0800. Min Act: -0.1700

Data Index: 7646238 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 6.4938. Min Range: -6.4938

Max Act: 6.0503. Min Act: -0.1700

Data Index: 6137991 (Open Web Text)

Max Activating Token Index: 595

Text #11

Max Range: 6.4938. Min Range: -6.4938

Max Act: 6.0241. Min Act: -0.1700

Data Index: 8477663 (Open Web Text)

Max Activating Token Index: 953

Text #12

Max Range: 6.4938. Min Range: -6.4938

Max Act: 6.0549. Min Act: -0.1700

Data Index: 3772592 (Open Web Text)

Max Activating Token Index: 40

Text #13

Max Range: 6.4938. Min Range: -6.4938

Max Act: 6.0429. Min Act: -0.1700

Data Index: 1154014 (Open Web Text)

Max Activating Token Index: 102

Text #14

Max Range: 6.4938. Min Range: -6.4938

Max Act: 6.0389. Min Act: -0.1700

Data Index: 8210067 (Open Web Text)

Max Activating Token Index: 620

Text #15

Max Range: 6.4938. Min Range: -6.4938

Max Act: 6.0441. Min Act: -0.1700

Data Index: 5690059 (Open Web Text)

Max Activating Token Index: 33

Text #16

Max Range: 6.4938. Min Range: -6.4938

Max Act: 6.0521. Min Act: -0.1700

Data Index: 1197152 (Open Web Text)

Max Activating Token Index: 331

Text #17

Max Range: 6.4938. Min Range: -6.4938

Max Act: 6.0576. Min Act: -0.1700

Data Index: 6288978 (Open Web Text)

Max Activating Token Index: 139

Text #18

Max Range: 6.4938. Min Range: -6.4938

Max Act: 6.0272. Min Act: -0.1700

Data Index: 6737346 (Open Web Text)

Max Activating Token Index: 320

Text #19

Max Range: 6.4938. Min Range: -6.4938

Max Act: 6.0412. Min Act: -0.1700

Data Index: 6381679 (Open Web Text)

Max Activating Token Index: 6