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

Dataset: Open Web Text

Neuron 2072 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: 3.3853. Min Range: -3.3853

Max Act: 3.3853. Min Act: -0.1700

Data Index: 416573 (Open Web Text)

Max Activating Token Index: 1008

Text #1

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.3737. Min Act: -0.1700

Data Index: 5905033 (Open Web Text)

Max Activating Token Index: 856

Text #2

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.3189. Min Act: -0.1700

Data Index: 150620 (Open Web Text)

Max Activating Token Index: 385

Text #3

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.3071. Min Act: -0.1700

Data Index: 761931 (Open Web Text)

Max Activating Token Index: 596

Text #4

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.2584. Min Act: -0.1700

Data Index: 1525400 (Open Web Text)

Max Activating Token Index: 761

Text #5

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.2849. Min Act: -0.1700

Data Index: 1755678 (Open Web Text)

Max Activating Token Index: 622

Text #6

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.2767. Min Act: -0.1700

Data Index: 989157 (Open Web Text)

Max Activating Token Index: 297

Text #7

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.2527. Min Act: -0.1700

Data Index: 149789 (Open Web Text)

Max Activating Token Index: 590

Text #8

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.2369. Min Act: -0.1700

Data Index: 4741024 (Open Web Text)

Max Activating Token Index: 188

Text #9

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.2397. Min Act: -0.1700

Data Index: 7142732 (Open Web Text)

Max Activating Token Index: 538

Text #10

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.2209. Min Act: -0.1700

Data Index: 7128523 (Open Web Text)

Max Activating Token Index: 854

Text #11

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.2160. Min Act: -0.1700

Data Index: 340655 (Open Web Text)

Max Activating Token Index: 527

Text #12

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.2050. Min Act: -0.1700

Data Index: 1001559 (Open Web Text)

Max Activating Token Index: 616

Text #13

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.2026. Min Act: -0.1700

Data Index: 6629845 (Open Web Text)

Max Activating Token Index: 272

Text #14

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.2190. Min Act: -0.1700

Data Index: 7694050 (Open Web Text)

Max Activating Token Index: 649

Text #15

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.1992. Min Act: -0.1700

Data Index: 634410 (Open Web Text)

Max Activating Token Index: 711

Text #16

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.1785. Min Act: -0.1700

Data Index: 2191765 (Open Web Text)

Max Activating Token Index: 677

Text #17

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.1901. Min Act: -0.1700

Data Index: 7253091 (Open Web Text)

Max Activating Token Index: 526

Text #18

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.2043. Min Act: -0.1700

Data Index: 3422313 (Open Web Text)

Max Activating Token Index: 313

Text #19

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.1747. Min Act: -0.1700

Data Index: 3806956 (Open Web Text)

Max Activating Token Index: 975