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

Dataset: Open Web Text

Neuron 1903 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: 5.6402. Min Range: -5.6402

Max Act: 5.6402. Min Act: -0.1700

Data Index: 6848648 (Open Web Text)

Max Activating Token Index: 779

Text #1

Max Range: 5.6402. Min Range: -5.6402

Max Act: 5.4251. Min Act: -0.1700

Data Index: 6078479 (Open Web Text)

Max Activating Token Index: 877

Text #2

Max Range: 5.6402. Min Range: -5.6402

Max Act: 5.3841. Min Act: -0.1700

Data Index: 3940971 (Open Web Text)

Max Activating Token Index: 753

Text #3

Max Range: 5.6402. Min Range: -5.6402

Max Act: 5.2469. Min Act: -0.1700

Data Index: 2209268 (Open Web Text)

Max Activating Token Index: 166

Text #4

Max Range: 5.6402. Min Range: -5.6402

Max Act: 5.2791. Min Act: -0.1700

Data Index: 7695312 (Open Web Text)

Max Activating Token Index: 841

Text #5

Max Range: 5.6402. Min Range: -5.6402

Max Act: 5.2902. Min Act: -0.1700

Data Index: 760002 (Open Web Text)

Max Activating Token Index: 806

Text #6

Max Range: 5.6402. Min Range: -5.6402

Max Act: 5.3037. Min Act: -0.1700

Data Index: 3026122 (Open Web Text)

Max Activating Token Index: 550

Text #7

Max Range: 5.6402. Min Range: -5.6402

Max Act: 5.2462. Min Act: -0.1700

Data Index: 6634472 (Open Web Text)

Max Activating Token Index: 476

Text #8

Max Range: 5.6402. Min Range: -5.6402

Max Act: 5.2180. Min Act: -0.1700

Data Index: 2512784 (Open Web Text)

Max Activating Token Index: 745

Text #9

Max Range: 5.6402. Min Range: -5.6402

Max Act: 5.2310. Min Act: -0.1700

Data Index: 8358328 (Open Web Text)

Max Activating Token Index: 347

Text #10

Max Range: 5.6402. Min Range: -5.6402

Max Act: 5.2165. Min Act: -0.1700

Data Index: 2819153 (Open Web Text)

Max Activating Token Index: 37

Text #11

Max Range: 5.6402. Min Range: -5.6402

Max Act: 5.2684. Min Act: -0.1700

Data Index: 7929684 (Open Web Text)

Max Activating Token Index: 877

Text #12

Max Range: 5.6402. Min Range: -5.6402

Max Act: 5.2597. Min Act: -0.1700

Data Index: 647680 (Open Web Text)

Max Activating Token Index: 201

Text #13

Max Range: 5.6402. Min Range: -5.6402

Max Act: 5.2481. Min Act: -0.1700

Data Index: 2261616 (Open Web Text)

Max Activating Token Index: 357

Text #14

Max Range: 5.6402. Min Range: -5.6402

Max Act: 5.2094. Min Act: -0.1700

Data Index: 8698187 (Open Web Text)

Max Activating Token Index: 430

Text #15

Max Range: 5.6402. Min Range: -5.6402

Max Act: 5.1847. Min Act: -0.1700

Data Index: 2101157 (Open Web Text)

Max Activating Token Index: 748

Text #16

Max Range: 5.6402. Min Range: -5.6402

Max Act: 5.2146. Min Act: -0.1700

Data Index: 5299841 (Open Web Text)

Max Activating Token Index: 907

Text #17

Max Range: 5.6402. Min Range: -5.6402

Max Act: 5.1744. Min Act: -0.1700

Data Index: 3684839 (Open Web Text)

Max Activating Token Index: 666

Text #18

Max Range: 5.6402. Min Range: -5.6402

Max Act: 5.2053. Min Act: -0.1700

Data Index: 5782521 (Open Web Text)

Max Activating Token Index: 146

Text #19

Max Range: 5.6402. Min Range: -5.6402

Max Act: 5.1830. Min Act: -0.1700

Data Index: 855488 (Open Web Text)

Max Activating Token Index: 408