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

Dataset: Open Web Text

Neuron 959 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: 3.0746. Min Range: -3.0746

Max Act: 3.0746. Min Act: -0.1700

Data Index: 7936069 (Open Web Text)

Max Activating Token Index: 590

Text #1

Max Range: 3.0746. Min Range: -3.0746

Max Act: 3.0418. Min Act: -0.1700

Data Index: 8589482 (Open Web Text)

Max Activating Token Index: 141

Text #2

Max Range: 3.0746. Min Range: -3.0746

Max Act: 3.0084. Min Act: -0.1700

Data Index: 4550152 (Open Web Text)

Max Activating Token Index: 343

Text #3

Max Range: 3.0746. Min Range: -3.0746

Max Act: 3.0059. Min Act: -0.1700

Data Index: 8105427 (Open Web Text)

Max Activating Token Index: 437

Text #4

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.9964. Min Act: -0.1700

Data Index: 6882139 (Open Web Text)

Max Activating Token Index: 460

Text #5

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.9753. Min Act: -0.1700

Data Index: 3360229 (Open Web Text)

Max Activating Token Index: 630

Text #6

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.9891. Min Act: -0.1700

Data Index: 5412963 (Open Web Text)

Max Activating Token Index: 952

Text #7

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.9892. Min Act: -0.1700

Data Index: 6024897 (Open Web Text)

Max Activating Token Index: 284

Text #8

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.9837. Min Act: -0.1700

Data Index: 6024898 (Open Web Text)

Max Activating Token Index: 800

Text #9

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.9534. Min Act: -0.1700

Data Index: 3204562 (Open Web Text)

Max Activating Token Index: 354

Text #10

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.9832. Min Act: -0.1700

Data Index: 1859740 (Open Web Text)

Max Activating Token Index: 724

Text #11

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.9558. Min Act: -0.1700

Data Index: 420869 (Open Web Text)

Max Activating Token Index: 724

Text #12

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.9374. Min Act: -0.1700

Data Index: 6884167 (Open Web Text)

Max Activating Token Index: 896

Text #13

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.9466. Min Act: -0.1700

Data Index: 4229917 (Open Web Text)

Max Activating Token Index: 317

Text #14

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.9197. Min Act: -0.1700

Data Index: 7352316 (Open Web Text)

Max Activating Token Index: 996

Text #15

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.9508. Min Act: -0.1700

Data Index: 2707360 (Open Web Text)

Max Activating Token Index: 837

Text #16

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.9624. Min Act: -0.1700

Data Index: 244815 (Open Web Text)

Max Activating Token Index: 963

Text #17

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.9390. Min Act: -0.1700

Data Index: 1010251 (Open Web Text)

Max Activating Token Index: 998

Text #18

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.9249. Min Act: -0.1700

Data Index: 4883498 (Open Web Text)

Max Activating Token Index: 140

Text #19

Max Range: 3.0746. Min Range: -3.0746

Max Act: 2.9604. Min Act: -0.1700

Data Index: 3689680 (Open Web Text)

Max Activating Token Index: 413