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

Dataset: Open Web Text

Neuron 2580 in Layer 5

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: 5.2285. Min Range: -5.2285

Max Act: 5.2285. Min Act: -0.1700

Data Index: 6355275 (Open Web Text)

Max Activating Token Index: 801

Text #1

Max Range: 5.2285. Min Range: -5.2285

Max Act: 5.0414. Min Act: -0.1700

Data Index: 1793210 (Open Web Text)

Max Activating Token Index: 912

Text #2

Max Range: 5.2285. Min Range: -5.2285

Max Act: 5.0524. Min Act: -0.1700

Data Index: 590120 (Open Web Text)

Max Activating Token Index: 65

Text #3

Max Range: 5.2285. Min Range: -5.2285

Max Act: 5.0133. Min Act: -0.1700

Data Index: 360526 (Open Web Text)

Max Activating Token Index: 787

Text #4

Max Range: 5.2285. Min Range: -5.2285

Max Act: 5.0638. Min Act: -0.1700

Data Index: 5546322 (Open Web Text)

Max Activating Token Index: 786

Text #5

Max Range: 5.2285. Min Range: -5.2285

Max Act: 4.9795. Min Act: -0.1700

Data Index: 453806 (Open Web Text)

Max Activating Token Index: 666

Text #6

Max Range: 5.2285. Min Range: -5.2285

Max Act: 4.9933. Min Act: -0.1700

Data Index: 843691 (Open Web Text)

Max Activating Token Index: 388

Text #7

Max Range: 5.2285. Min Range: -5.2285

Max Act: 4.9864. Min Act: -0.1700

Data Index: 1793211 (Open Web Text)

Max Activating Token Index: 260

Text #8

Max Range: 5.2285. Min Range: -5.2285

Max Act: 4.9852. Min Act: -0.1700

Data Index: 6464449 (Open Web Text)

Max Activating Token Index: 408

Text #9

Max Range: 5.2285. Min Range: -5.2285

Max Act: 4.9443. Min Act: -0.1700

Data Index: 7633250 (Open Web Text)

Max Activating Token Index: 677

Text #10

Max Range: 5.2285. Min Range: -5.2285

Max Act: 4.9183. Min Act: -0.1700

Data Index: 5915785 (Open Web Text)

Max Activating Token Index: 572

Text #11

Max Range: 5.2285. Min Range: -5.2285

Max Act: 4.9487. Min Act: -0.1700

Data Index: 8756142 (Open Web Text)

Max Activating Token Index: 241

Text #12

Max Range: 5.2285. Min Range: -5.2285

Max Act: 4.9554. Min Act: -0.1700

Data Index: 8685772 (Open Web Text)

Max Activating Token Index: 77

Text #13

Max Range: 5.2285. Min Range: -5.2285

Max Act: 4.9274. Min Act: -0.1700

Data Index: 5756200 (Open Web Text)

Max Activating Token Index: 112

Text #14

Max Range: 5.2285. Min Range: -5.2285

Max Act: 4.9442. Min Act: -0.1700

Data Index: 6464448 (Open Web Text)

Max Activating Token Index: 211

Text #15

Max Range: 5.2285. Min Range: -5.2285

Max Act: 4.9301. Min Act: -0.1700

Data Index: 2353480 (Open Web Text)

Max Activating Token Index: 56

Text #16

Max Range: 5.2285. Min Range: -5.2285

Max Act: 4.9425. Min Act: -0.1700

Data Index: 5991185 (Open Web Text)

Max Activating Token Index: 623

Text #17

Max Range: 5.2285. Min Range: -5.2285

Max Act: 4.8854. Min Act: -0.1700

Data Index: 490692 (Open Web Text)

Max Activating Token Index: 120

Text #18

Max Range: 5.2285. Min Range: -5.2285

Max Act: 4.9560. Min Act: -0.1700

Data Index: 590121 (Open Web Text)

Max Activating Token Index: 500

Text #19

Max Range: 5.2285. Min Range: -5.2285

Max Act: 4.9015. Min Act: -0.1700

Data Index: 6615173 (Open Web Text)

Max Activating Token Index: 876