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

Dataset: Open Web Text

Neuron 587 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: 3.2872. Min Range: -3.2872

Max Act: 3.2872. Min Act: -0.1700

Data Index: 7284853 (Open Web Text)

Max Activating Token Index: 998

Text #1

Max Range: 3.2872. Min Range: -3.2872

Max Act: 3.2580. Min Act: -0.1700

Data Index: 2548409 (Open Web Text)

Max Activating Token Index: 309

Text #2

Max Range: 3.2872. Min Range: -3.2872

Max Act: 3.2086. Min Act: -0.1700

Data Index: 3326529 (Open Web Text)

Max Activating Token Index: 917

Text #3

Max Range: 3.2872. Min Range: -3.2872

Max Act: 3.2026. Min Act: -0.1700

Data Index: 3231732 (Open Web Text)

Max Activating Token Index: 615

Text #4

Max Range: 3.2872. Min Range: -3.2872

Max Act: 3.2152. Min Act: -0.1700

Data Index: 5531776 (Open Web Text)

Max Activating Token Index: 616

Text #5

Max Range: 3.2872. Min Range: -3.2872

Max Act: 3.1988. Min Act: -0.1700

Data Index: 1816402 (Open Web Text)

Max Activating Token Index: 149

Text #6

Max Range: 3.2872. Min Range: -3.2872

Max Act: 3.2038. Min Act: -0.1700

Data Index: 2253898 (Open Web Text)

Max Activating Token Index: 391

Text #7

Max Range: 3.2872. Min Range: -3.2872

Max Act: 3.1619. Min Act: -0.1700

Data Index: 4578691 (Open Web Text)

Max Activating Token Index: 962

Text #8

Max Range: 3.2872. Min Range: -3.2872

Max Act: 3.1777. Min Act: -0.1700

Data Index: 1460557 (Open Web Text)

Max Activating Token Index: 318

Text #9

Max Range: 3.2872. Min Range: -3.2872

Max Act: 3.1866. Min Act: -0.1700

Data Index: 3099404 (Open Web Text)

Max Activating Token Index: 261

Text #10

Max Range: 3.2872. Min Range: -3.2872

Max Act: 3.1868. Min Act: -0.1700

Data Index: 6811076 (Open Web Text)

Max Activating Token Index: 416

Text #11

Max Range: 3.2872. Min Range: -3.2872

Max Act: 3.1579. Min Act: -0.1700

Data Index: 1739200 (Open Web Text)

Max Activating Token Index: 75

Text #12

Max Range: 3.2872. Min Range: -3.2872

Max Act: 3.1401. Min Act: -0.1700

Data Index: 2274677 (Open Web Text)

Max Activating Token Index: 728

Text #13

Max Range: 3.2872. Min Range: -3.2872

Max Act: 3.1915. Min Act: -0.1700

Data Index: 339351 (Open Web Text)

Max Activating Token Index: 524

Text #14

Max Range: 3.2872. Min Range: -3.2872

Max Act: 3.1653. Min Act: -0.1700

Data Index: 8064621 (Open Web Text)

Max Activating Token Index: 786

Text #15

Max Range: 3.2872. Min Range: -3.2872

Max Act: 3.1547. Min Act: -0.1700

Data Index: 1315161 (Open Web Text)

Max Activating Token Index: 176

Text #16

Max Range: 3.2872. Min Range: -3.2872

Max Act: 3.1606. Min Act: -0.1700

Data Index: 7249181 (Open Web Text)

Max Activating Token Index: 812

Text #17

Max Range: 3.2872. Min Range: -3.2872

Max Act: 3.1624. Min Act: -0.1700

Data Index: 2856664 (Open Web Text)

Max Activating Token Index: 186

Text #18

Max Range: 3.2872. Min Range: -3.2872

Max Act: 3.1402. Min Act: -0.1700

Data Index: 4073238 (Open Web Text)

Max Activating Token Index: 343

Text #19

Max Range: 3.2872. Min Range: -3.2872

Max Act: 3.1543. Min Act: -0.1700

Data Index: 3291569 (Open Web Text)

Max Activating Token Index: 849