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

Dataset: Open Web Text

Neuron 2784 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: 3.3892. Min Range: -3.3892

Max Act: 3.3800. Min Act: -0.1700

Data Index: 941639 (Open Web Text)

Max Activating Token Index: 201

Text #1

Max Range: 3.3892. Min Range: -3.3892

Max Act: 3.3892. Min Act: -0.1700

Data Index: 6611213 (Open Web Text)

Max Activating Token Index: 993

Text #2

Max Range: 3.3892. Min Range: -3.3892

Max Act: 3.3596. Min Act: -0.1700

Data Index: 5889182 (Open Web Text)

Max Activating Token Index: 329

Text #3

Max Range: 3.3892. Min Range: -3.3892

Max Act: 3.3456. Min Act: -0.1700

Data Index: 432829 (Open Web Text)

Max Activating Token Index: 427

Text #4

Max Range: 3.3892. Min Range: -3.3892

Max Act: 3.3201. Min Act: -0.1700

Data Index: 6360143 (Open Web Text)

Max Activating Token Index: 563

Text #5

Max Range: 3.3892. Min Range: -3.3892

Max Act: 3.3046. Min Act: -0.1700

Data Index: 4195002 (Open Web Text)

Max Activating Token Index: 707

Text #6

Max Range: 3.3892. Min Range: -3.3892

Max Act: 3.3107. Min Act: -0.1700

Data Index: 4592595 (Open Web Text)

Max Activating Token Index: 292

Text #7

Max Range: 3.3892. Min Range: -3.3892

Max Act: 3.2962. Min Act: -0.1700

Data Index: 3393801 (Open Web Text)

Max Activating Token Index: 655

Text #8

Max Range: 3.3892. Min Range: -3.3892

Max Act: 3.2862. Min Act: -0.1700

Data Index: 6406814 (Open Web Text)

Max Activating Token Index: 685

Text #9

Max Range: 3.3892. Min Range: -3.3892

Max Act: 3.2870. Min Act: -0.1700

Data Index: 929444 (Open Web Text)

Max Activating Token Index: 363

Text #10

Max Range: 3.3892. Min Range: -3.3892

Max Act: 3.2901. Min Act: -0.1700

Data Index: 7547587 (Open Web Text)

Max Activating Token Index: 236

Text #11

Max Range: 3.3892. Min Range: -3.3892

Max Act: 3.2993. Min Act: -0.1700

Data Index: 2470534 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 3.3892. Min Range: -3.3892

Max Act: 3.2778. Min Act: -0.1700

Data Index: 4463852 (Open Web Text)

Max Activating Token Index: 743

Text #13

Max Range: 3.3892. Min Range: -3.3892

Max Act: 3.2819. Min Act: -0.1700

Data Index: 3805120 (Open Web Text)

Max Activating Token Index: 470

Text #14

Max Range: 3.3892. Min Range: -3.3892

Max Act: 3.2654. Min Act: -0.1700

Data Index: 3017460 (Open Web Text)

Max Activating Token Index: 376

Text #15

Max Range: 3.3892. Min Range: -3.3892

Max Act: 3.2440. Min Act: -0.1700

Data Index: 4741529 (Open Web Text)

Max Activating Token Index: 163

Text #16

Max Range: 3.3892. Min Range: -3.3892

Max Act: 3.2760. Min Act: -0.1700

Data Index: 4805758 (Open Web Text)

Max Activating Token Index: 391

Text #17

Max Range: 3.3892. Min Range: -3.3892

Max Act: 3.2753. Min Act: -0.1700

Data Index: 4327794 (Open Web Text)

Max Activating Token Index: 484

Text #18

Max Range: 3.3892. Min Range: -3.3892

Max Act: 3.2345. Min Act: -0.1700

Data Index: 2788359 (Open Web Text)

Max Activating Token Index: 391

Text #19

Max Range: 3.3892. Min Range: -3.3892

Max Act: 3.2718. Min Act: -0.1700

Data Index: 7102704 (Open Web Text)

Max Activating Token Index: 261