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

Dataset: Open Web Text

Neuron 1082 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: 1.9841. Min Range: -1.9841

Max Act: 1.9841. Min Act: -0.1700

Data Index: 7631954 (Open Web Text)

Max Activating Token Index: 210

Text #1

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.9583. Min Act: -0.1700

Data Index: 4923421 (Open Web Text)

Max Activating Token Index: 948

Text #2

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.9365. Min Act: -0.1700

Data Index: 6350184 (Open Web Text)

Max Activating Token Index: 69

Text #3

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.9381. Min Act: -0.1700

Data Index: 1954625 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.9460. Min Act: -0.1700

Data Index: 7690215 (Open Web Text)

Max Activating Token Index: 304

Text #5

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.9267. Min Act: -0.1700

Data Index: 7456206 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.9260. Min Act: -0.1700

Data Index: 394104 (Open Web Text)

Max Activating Token Index: 225

Text #7

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.9344. Min Act: -0.1700

Data Index: 343140 (Open Web Text)

Max Activating Token Index: 473

Text #8

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.8829. Min Act: -0.1700

Data Index: 3623781 (Open Web Text)

Max Activating Token Index: 16

Text #9

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.8802. Min Act: -0.1700

Data Index: 1545114 (Open Web Text)

Max Activating Token Index: 820

Text #10

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.8699. Min Act: -0.1698

Data Index: 2159094 (Open Web Text)

Max Activating Token Index: 506

Text #11

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.8608. Min Act: -0.1700

Data Index: 4126407 (Open Web Text)

Max Activating Token Index: 434

Text #12

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.8540. Min Act: -0.1700

Data Index: 4007389 (Open Web Text)

Max Activating Token Index: 643

Text #13

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.8626. Min Act: -0.1700

Data Index: 1448884 (Open Web Text)

Max Activating Token Index: 87

Text #14

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.8663. Min Act: -0.1700

Data Index: 2849187 (Open Web Text)

Max Activating Token Index: 41

Text #15

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.8561. Min Act: -0.1700

Data Index: 3164316 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.8563. Min Act: -0.1700

Data Index: 807233 (Open Web Text)

Max Activating Token Index: 231

Text #17

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.8553. Min Act: -0.1700

Data Index: 7111518 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.8412. Min Act: -0.1700

Data Index: 3948806 (Open Web Text)

Max Activating Token Index: 834

Text #19

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.8401. Min Act: -0.1700

Data Index: 6139757 (Open Web Text)

Max Activating Token Index: 913