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

Dataset: Open Web Text

Neuron 325 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: 4.6433. Min Range: -4.6433

Max Act: 4.6433. Min Act: -0.1700

Data Index: 2013828 (Open Web Text)

Max Activating Token Index: 455

Text #1

Max Range: 4.6433. Min Range: -4.6433

Max Act: 4.5365. Min Act: -0.1700

Data Index: 5711074 (Open Web Text)

Max Activating Token Index: 794

Text #2

Max Range: 4.6433. Min Range: -4.6433

Max Act: 4.5312. Min Act: -0.1700

Data Index: 1740413 (Open Web Text)

Max Activating Token Index: 161

Text #3

Max Range: 4.6433. Min Range: -4.6433

Max Act: 4.5449. Min Act: -0.1700

Data Index: 5490535 (Open Web Text)

Max Activating Token Index: 663

Text #4

Max Range: 4.6433. Min Range: -4.6433

Max Act: 4.5210. Min Act: -0.1700

Data Index: 409293 (Open Web Text)

Max Activating Token Index: 202

Text #5

Max Range: 4.6433. Min Range: -4.6433

Max Act: 4.5208. Min Act: -0.1700

Data Index: 2912560 (Open Web Text)

Max Activating Token Index: 424

Text #6

Max Range: 4.6433. Min Range: -4.6433

Max Act: 4.5399. Min Act: -0.1700

Data Index: 7825321 (Open Web Text)

Max Activating Token Index: 122

Text #7

Max Range: 4.6433. Min Range: -4.6433

Max Act: 4.4875. Min Act: -0.1700

Data Index: 8807674 (Open Web Text)

Max Activating Token Index: 449

Text #8

Max Range: 4.6433. Min Range: -4.6433

Max Act: 4.4203. Min Act: -0.1700

Data Index: 6482430 (Open Web Text)

Max Activating Token Index: 707

Text #9

Max Range: 4.6433. Min Range: -4.6433

Max Act: 4.3774. Min Act: -0.1700

Data Index: 8715044 (Open Web Text)

Max Activating Token Index: 200

Text #10

Max Range: 4.6433. Min Range: -4.6433

Max Act: 4.3722. Min Act: -0.1700

Data Index: 6750900 (Open Web Text)

Max Activating Token Index: 268

Text #11

Max Range: 4.6433. Min Range: -4.6433

Max Act: 4.3694. Min Act: -0.1700

Data Index: 1547263 (Open Web Text)

Max Activating Token Index: 402

Text #12

Max Range: 4.6433. Min Range: -4.6433

Max Act: 4.3699. Min Act: -0.1700

Data Index: 8381017 (Open Web Text)

Max Activating Token Index: 764

Text #13

Max Range: 4.6433. Min Range: -4.6433

Max Act: 4.3832. Min Act: -0.1700

Data Index: 4751359 (Open Web Text)

Max Activating Token Index: 681

Text #14

Max Range: 4.6433. Min Range: -4.6433

Max Act: 4.3698. Min Act: -0.1700

Data Index: 6427447 (Open Web Text)

Max Activating Token Index: 743

Text #15

Max Range: 4.6433. Min Range: -4.6433

Max Act: 4.3839. Min Act: -0.1700

Data Index: 6088901 (Open Web Text)

Max Activating Token Index: 578

Text #16

Max Range: 4.6433. Min Range: -4.6433

Max Act: 4.3347. Min Act: -0.1700

Data Index: 5383910 (Open Web Text)

Max Activating Token Index: 537

Text #17

Max Range: 4.6433. Min Range: -4.6433

Max Act: 4.3847. Min Act: -0.1700

Data Index: 6898951 (Open Web Text)

Max Activating Token Index: 784

Text #18

Max Range: 4.6433. Min Range: -4.6433

Max Act: 4.3360. Min Act: -0.1700

Data Index: 369195 (Open Web Text)

Max Activating Token Index: 276

Text #19

Max Range: 4.6433. Min Range: -4.6433

Max Act: 4.3294. Min Act: -0.1700

Data Index: 8573291 (Open Web Text)

Max Activating Token Index: 342