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

Dataset: Open Web Text

Neuron 1871 in Layer 2

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: 3.2227. Min Range: -3.2227

Max Act: 3.2227. Min Act: -0.1700

Data Index: 4251119 (Open Web Text)

Max Activating Token Index: 784

Text #1

Max Range: 3.2227. Min Range: -3.2227

Max Act: 3.1835. Min Act: -0.1700

Data Index: 5404538 (Open Web Text)

Max Activating Token Index: 974

Text #2

Max Range: 3.2227. Min Range: -3.2227

Max Act: 3.1458. Min Act: -0.1700

Data Index: 611430 (Open Web Text)

Max Activating Token Index: 748

Text #3

Max Range: 3.2227. Min Range: -3.2227

Max Act: 3.1303. Min Act: -0.1700

Data Index: 7918417 (Open Web Text)

Max Activating Token Index: 849

Text #4

Max Range: 3.2227. Min Range: -3.2227

Max Act: 3.0955. Min Act: -0.1700

Data Index: 3771063 (Open Web Text)

Max Activating Token Index: 513

Text #5

Max Range: 3.2227. Min Range: -3.2227

Max Act: 3.0877. Min Act: -0.1700

Data Index: 1818828 (Open Web Text)

Max Activating Token Index: 173

Text #6

Max Range: 3.2227. Min Range: -3.2227

Max Act: 3.1075. Min Act: -0.1700

Data Index: 5127115 (Open Web Text)

Max Activating Token Index: 1019

Text #7

Max Range: 3.2227. Min Range: -3.2227

Max Act: 3.1035. Min Act: -0.1700

Data Index: 7119531 (Open Web Text)

Max Activating Token Index: 636

Text #8

Max Range: 3.2227. Min Range: -3.2227

Max Act: 3.0716. Min Act: -0.1700

Data Index: 545217 (Open Web Text)

Max Activating Token Index: 185

Text #9

Max Range: 3.2227. Min Range: -3.2227

Max Act: 3.0845. Min Act: -0.1700

Data Index: 4749750 (Open Web Text)

Max Activating Token Index: 320

Text #10

Max Range: 3.2227. Min Range: -3.2227

Max Act: 3.0912. Min Act: -0.1700

Data Index: 8547138 (Open Web Text)

Max Activating Token Index: 185

Text #11

Max Range: 3.2227. Min Range: -3.2227

Max Act: 3.0844. Min Act: -0.1700

Data Index: 4085866 (Open Web Text)

Max Activating Token Index: 619

Text #12

Max Range: 3.2227. Min Range: -3.2227

Max Act: 3.0350. Min Act: -0.1700

Data Index: 280057 (Open Web Text)

Max Activating Token Index: 984

Text #13

Max Range: 3.2227. Min Range: -3.2227

Max Act: 3.0336. Min Act: -0.1700

Data Index: 130786 (Open Web Text)

Max Activating Token Index: 472

Text #14

Max Range: 3.2227. Min Range: -3.2227

Max Act: 3.0343. Min Act: -0.1700

Data Index: 6896200 (Open Web Text)

Max Activating Token Index: 763

Text #15

Max Range: 3.2227. Min Range: -3.2227

Max Act: 3.0181. Min Act: -0.1700

Data Index: 3168241 (Open Web Text)

Max Activating Token Index: 191

Text #16

Max Range: 3.2227. Min Range: -3.2227

Max Act: 3.0184. Min Act: -0.1700

Data Index: 1276988 (Open Web Text)

Max Activating Token Index: 963

Text #17

Max Range: 3.2227. Min Range: -3.2227

Max Act: 3.0257. Min Act: -0.1700

Data Index: 2243372 (Open Web Text)

Max Activating Token Index: 971

Text #18

Max Range: 3.2227. Min Range: -3.2227

Max Act: 2.9967. Min Act: -0.1700

Data Index: 3082463 (Open Web Text)

Max Activating Token Index: 485

Text #19

Max Range: 3.2227. Min Range: -3.2227

Max Act: 3.0020. Min Act: -0.1700

Data Index: 1152534 (Open Web Text)

Max Activating Token Index: 980