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

Dataset: Open Web Text

Neuron 1887 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: 4.3951. Min Range: -4.3951

Max Act: 4.3947. Min Act: -0.1700

Data Index: 424594 (Open Web Text)

Max Activating Token Index: 234

Text #1

Max Range: 4.3951. Min Range: -4.3951

Max Act: 4.3911. Min Act: -0.1700

Data Index: 1735193 (Open Web Text)

Max Activating Token Index: 935

Text #2

Max Range: 4.3951. Min Range: -4.3951

Max Act: 4.3951. Min Act: -0.1700

Data Index: 1674456 (Open Web Text)

Max Activating Token Index: 483

Text #3

Max Range: 4.3951. Min Range: -4.3951

Max Act: 4.3296. Min Act: -0.1700

Data Index: 1872428 (Open Web Text)

Max Activating Token Index: 590

Text #4

Max Range: 4.3951. Min Range: -4.3951

Max Act: 4.3480. Min Act: -0.1700

Data Index: 6412388 (Open Web Text)

Max Activating Token Index: 272

Text #5

Max Range: 4.3951. Min Range: -4.3951

Max Act: 4.3378. Min Act: -0.1700

Data Index: 3591740 (Open Web Text)

Max Activating Token Index: 471

Text #6

Max Range: 4.3951. Min Range: -4.3951

Max Act: 4.2937. Min Act: -0.1700

Data Index: 2473655 (Open Web Text)

Max Activating Token Index: 586

Text #7

Max Range: 4.3951. Min Range: -4.3951

Max Act: 4.2887. Min Act: -0.1700

Data Index: 5149093 (Open Web Text)

Max Activating Token Index: 880

Text #8

Max Range: 4.3951. Min Range: -4.3951

Max Act: 4.2396. Min Act: -0.1700

Data Index: 3501625 (Open Web Text)

Max Activating Token Index: 702

Text #9

Max Range: 4.3951. Min Range: -4.3951

Max Act: 4.2510. Min Act: -0.1700

Data Index: 486920 (Open Web Text)

Max Activating Token Index: 461

Text #10

Max Range: 4.3951. Min Range: -4.3951

Max Act: 4.2524. Min Act: -0.1700

Data Index: 5410093 (Open Web Text)

Max Activating Token Index: 494

Text #11

Max Range: 4.3951. Min Range: -4.3951

Max Act: 4.2125. Min Act: -0.1700

Data Index: 1622393 (Open Web Text)

Max Activating Token Index: 628

Text #12

Max Range: 4.3951. Min Range: -4.3951

Max Act: 4.2477. Min Act: -0.1700

Data Index: 227613 (Open Web Text)

Max Activating Token Index: 966

Text #13

Max Range: 4.3951. Min Range: -4.3951

Max Act: 4.2374. Min Act: -0.1700

Data Index: 2552927 (Open Web Text)

Max Activating Token Index: 369

Text #14

Max Range: 4.3951. Min Range: -4.3951

Max Act: 4.2101. Min Act: -0.1700

Data Index: 8812409 (Open Web Text)

Max Activating Token Index: 970

Text #15

Max Range: 4.3951. Min Range: -4.3951

Max Act: 4.1923. Min Act: -0.1700

Data Index: 392044 (Open Web Text)

Max Activating Token Index: 950

Text #16

Max Range: 4.3951. Min Range: -4.3951

Max Act: 4.2410. Min Act: -0.1700

Data Index: 3656785 (Open Web Text)

Max Activating Token Index: 390

Text #17

Max Range: 4.3951. Min Range: -4.3951

Max Act: 4.2159. Min Act: -0.1700

Data Index: 2065022 (Open Web Text)

Max Activating Token Index: 883

Text #18

Max Range: 4.3951. Min Range: -4.3951

Max Act: 4.2036. Min Act: -0.1700

Data Index: 3613384 (Open Web Text)

Max Activating Token Index: 398

Text #19

Max Range: 4.3951. Min Range: -4.3951

Max Act: 4.1800. Min Act: -0.1700

Data Index: 5090057 (Open Web Text)

Max Activating Token Index: 890