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

Dataset: Open Web Text

Neuron 1756 in Layer 4

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: 3.3759. Min Range: -3.3759

Max Act: 3.3759. Min Act: -0.1700

Data Index: 7451612 (Open Web Text)

Max Activating Token Index: 238

Text #1

Max Range: 3.3759. Min Range: -3.3759

Max Act: 3.3542. Min Act: -0.1700

Data Index: 8671698 (Open Web Text)

Max Activating Token Index: 130

Text #2

Max Range: 3.3759. Min Range: -3.3759

Max Act: 3.3552. Min Act: -0.1700

Data Index: 657317 (Open Web Text)

Max Activating Token Index: 282

Text #3

Max Range: 3.3759. Min Range: -3.3759

Max Act: 3.3547. Min Act: -0.1700

Data Index: 5041332 (Open Web Text)

Max Activating Token Index: 741

Text #4

Max Range: 3.3759. Min Range: -3.3759

Max Act: 3.3238. Min Act: -0.1700

Data Index: 595413 (Open Web Text)

Max Activating Token Index: 566

Text #5

Max Range: 3.3759. Min Range: -3.3759

Max Act: 3.2875. Min Act: -0.1700

Data Index: 8827864 (Open Web Text)

Max Activating Token Index: 464

Text #6

Max Range: 3.3759. Min Range: -3.3759

Max Act: 3.3026. Min Act: -0.1700

Data Index: 7971094 (Open Web Text)

Max Activating Token Index: 235

Text #7

Max Range: 3.3759. Min Range: -3.3759

Max Act: 3.2541. Min Act: -0.1700

Data Index: 7919805 (Open Web Text)

Max Activating Token Index: 181

Text #8

Max Range: 3.3759. Min Range: -3.3759

Max Act: 3.2706. Min Act: -0.1700

Data Index: 3407515 (Open Web Text)

Max Activating Token Index: 781

Text #9

Max Range: 3.3759. Min Range: -3.3759

Max Act: 3.2581. Min Act: -0.1700

Data Index: 5173377 (Open Web Text)

Max Activating Token Index: 782

Text #10

Max Range: 3.3759. Min Range: -3.3759

Max Act: 3.2361. Min Act: -0.1700

Data Index: 3428735 (Open Web Text)

Max Activating Token Index: 543

Text #11

Max Range: 3.3759. Min Range: -3.3759

Max Act: 3.2363. Min Act: -0.1700

Data Index: 5600183 (Open Web Text)

Max Activating Token Index: 966

Text #12

Max Range: 3.3759. Min Range: -3.3759

Max Act: 3.2490. Min Act: -0.1700

Data Index: 4742278 (Open Web Text)

Max Activating Token Index: 754

Text #13

Max Range: 3.3759. Min Range: -3.3759

Max Act: 3.2623. Min Act: -0.1700

Data Index: 3212741 (Open Web Text)

Max Activating Token Index: 36

Text #14

Max Range: 3.3759. Min Range: -3.3759

Max Act: 3.2576. Min Act: -0.1700

Data Index: 4690334 (Open Web Text)

Max Activating Token Index: 583

Text #15

Max Range: 3.3759. Min Range: -3.3759

Max Act: 3.2481. Min Act: -0.1700

Data Index: 2207966 (Open Web Text)

Max Activating Token Index: 49

Text #16

Max Range: 3.3759. Min Range: -3.3759

Max Act: 3.2164. Min Act: -0.1700

Data Index: 710039 (Open Web Text)

Max Activating Token Index: 899

Text #17

Max Range: 3.3759. Min Range: -3.3759

Max Act: 3.2146. Min Act: -0.1700

Data Index: 2877814 (Open Web Text)

Max Activating Token Index: 493

Text #18

Max Range: 3.3759. Min Range: -3.3759

Max Act: 3.2377. Min Act: -0.1700

Data Index: 5099936 (Open Web Text)

Max Activating Token Index: 85

Text #19

Max Range: 3.3759. Min Range: -3.3759

Max Act: 3.2292. Min Act: -0.1700

Data Index: 115408 (Open Web Text)

Max Activating Token Index: 211