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

Dataset: Open Web Text

Neuron 447 in Layer 6

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: 3.0764. Min Range: -3.0764

Max Act: 3.0764. Min Act: -0.1700

Data Index: 5748552 (Open Web Text)

Max Activating Token Index: 806

Text #1

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.9154. Min Act: -0.1700

Data Index: 6913379 (Open Web Text)

Max Activating Token Index: 393

Text #2

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.9146. Min Act: -0.1700

Data Index: 1227316 (Open Web Text)

Max Activating Token Index: 643

Text #3

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.8952. Min Act: -0.1700

Data Index: 5766178 (Open Web Text)

Max Activating Token Index: 339

Text #4

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.8465. Min Act: -0.1700

Data Index: 334297 (Open Web Text)

Max Activating Token Index: 581

Text #5

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.8471. Min Act: -0.1700

Data Index: 7267863 (Open Web Text)

Max Activating Token Index: 464

Text #6

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.8351. Min Act: -0.1700

Data Index: 4860074 (Open Web Text)

Max Activating Token Index: 966

Text #7

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.8214. Min Act: -0.1700

Data Index: 7997753 (Open Web Text)

Max Activating Token Index: 826

Text #8

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.8302. Min Act: -0.1700

Data Index: 7873985 (Open Web Text)

Max Activating Token Index: 447

Text #9

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.8697. Min Act: -0.1700

Data Index: 7789307 (Open Web Text)

Max Activating Token Index: 447

Text #10

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.7893. Min Act: -0.1700

Data Index: 3373291 (Open Web Text)

Max Activating Token Index: 1002

Text #11

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.8148. Min Act: -0.1700

Data Index: 67774 (Open Web Text)

Max Activating Token Index: 178

Text #12

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.8119. Min Act: -0.1700

Data Index: 6536233 (Open Web Text)

Max Activating Token Index: 721

Text #13

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.8025. Min Act: -0.1700

Data Index: 1253774 (Open Web Text)

Max Activating Token Index: 413

Text #14

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.7800. Min Act: -0.1700

Data Index: 7413020 (Open Web Text)

Max Activating Token Index: 621

Text #15

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.7735. Min Act: -0.1700

Data Index: 7569645 (Open Web Text)

Max Activating Token Index: 489

Text #16

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.7934. Min Act: -0.1700

Data Index: 7412128 (Open Web Text)

Max Activating Token Index: 461

Text #17

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.7771. Min Act: -0.1700

Data Index: 4698698 (Open Web Text)

Max Activating Token Index: 571

Text #18

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.7859. Min Act: -0.1700

Data Index: 5702860 (Open Web Text)

Max Activating Token Index: 180

Text #19

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.7799. Min Act: -0.1700

Data Index: 1922952 (Open Web Text)

Max Activating Token Index: 762