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

Dataset: Open Web Text

Neuron 61 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: 3.3800. Min Range: -3.3800

Max Act: 3.3800. Min Act: -0.1700

Data Index: 8740936 (Open Web Text)

Max Activating Token Index: 477

Text #1

Max Range: 3.3800. Min Range: -3.3800

Max Act: 3.3764. Min Act: -0.1700

Data Index: 4251921 (Open Web Text)

Max Activating Token Index: 831

Text #2

Max Range: 3.3800. Min Range: -3.3800

Max Act: 3.3706. Min Act: -0.1700

Data Index: 4739171 (Open Web Text)

Max Activating Token Index: 163

Text #3

Max Range: 3.3800. Min Range: -3.3800

Max Act: 3.3498. Min Act: -0.1700

Data Index: 8242555 (Open Web Text)

Max Activating Token Index: 948

Text #4

Max Range: 3.3800. Min Range: -3.3800

Max Act: 3.3434. Min Act: -0.1700

Data Index: 7658045 (Open Web Text)

Max Activating Token Index: 542

Text #5

Max Range: 3.3800. Min Range: -3.3800

Max Act: 3.3533. Min Act: -0.1700

Data Index: 6880330 (Open Web Text)

Max Activating Token Index: 593

Text #6

Max Range: 3.3800. Min Range: -3.3800

Max Act: 3.2854. Min Act: -0.1700

Data Index: 6042985 (Open Web Text)

Max Activating Token Index: 1021

Text #7

Max Range: 3.3800. Min Range: -3.3800

Max Act: 3.3232. Min Act: -0.1700

Data Index: 7165392 (Open Web Text)

Max Activating Token Index: 123

Text #8

Max Range: 3.3800. Min Range: -3.3800

Max Act: 3.3119. Min Act: -0.1700

Data Index: 1802667 (Open Web Text)

Max Activating Token Index: 265

Text #9

Max Range: 3.3800. Min Range: -3.3800

Max Act: 3.3274. Min Act: -0.1700

Data Index: 477891 (Open Web Text)

Max Activating Token Index: 346

Text #10

Max Range: 3.3800. Min Range: -3.3800

Max Act: 3.3191. Min Act: -0.1700

Data Index: 6612936 (Open Web Text)

Max Activating Token Index: 778

Text #11

Max Range: 3.3800. Min Range: -3.3800

Max Act: 3.3302. Min Act: -0.1700

Data Index: 8449035 (Open Web Text)

Max Activating Token Index: 616

Text #12

Max Range: 3.3800. Min Range: -3.3800

Max Act: 3.3230. Min Act: -0.1700

Data Index: 6968382 (Open Web Text)

Max Activating Token Index: 302

Text #13

Max Range: 3.3800. Min Range: -3.3800

Max Act: 3.2993. Min Act: -0.1700

Data Index: 5568389 (Open Web Text)

Max Activating Token Index: 636

Text #14

Max Range: 3.3800. Min Range: -3.3800

Max Act: 3.2979. Min Act: -0.1700

Data Index: 5653370 (Open Web Text)

Max Activating Token Index: 317

Text #15

Max Range: 3.3800. Min Range: -3.3800

Max Act: 3.2915. Min Act: -0.1700

Data Index: 2148338 (Open Web Text)

Max Activating Token Index: 322

Text #16

Max Range: 3.3800. Min Range: -3.3800

Max Act: 3.2625. Min Act: -0.1700

Data Index: 5335765 (Open Web Text)

Max Activating Token Index: 140

Text #17

Max Range: 3.3800. Min Range: -3.3800

Max Act: 3.2969. Min Act: -0.1700

Data Index: 1469700 (Open Web Text)

Max Activating Token Index: 543

Text #18

Max Range: 3.3800. Min Range: -3.3800

Max Act: 3.2955. Min Act: -0.1700

Data Index: 4213917 (Open Web Text)

Max Activating Token Index: 343

Text #19

Max Range: 3.3800. Min Range: -3.3800

Max Act: 3.2707. Min Act: -0.1700

Data Index: 982710 (Open Web Text)

Max Activating Token Index: 195