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

Dataset: Open Web Text

Neuron 994 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: 4.2464. Min Range: -4.2464

Max Act: 4.2464. Min Act: -0.1700

Data Index: 8134638 (Open Web Text)

Max Activating Token Index: 730

Text #1

Max Range: 4.2464. Min Range: -4.2464

Max Act: 4.1089. Min Act: -0.1700

Data Index: 2723867 (Open Web Text)

Max Activating Token Index: 690

Text #2

Max Range: 4.2464. Min Range: -4.2464

Max Act: 4.0883. Min Act: -0.1700

Data Index: 5149765 (Open Web Text)

Max Activating Token Index: 602

Text #3

Max Range: 4.2464. Min Range: -4.2464

Max Act: 4.1120. Min Act: -0.1700

Data Index: 4960967 (Open Web Text)

Max Activating Token Index: 235

Text #4

Max Range: 4.2464. Min Range: -4.2464

Max Act: 4.1142. Min Act: -0.1700

Data Index: 3996658 (Open Web Text)

Max Activating Token Index: 457

Text #5

Max Range: 4.2464. Min Range: -4.2464

Max Act: 4.0846. Min Act: -0.1700

Data Index: 734154 (Open Web Text)

Max Activating Token Index: 710

Text #6

Max Range: 4.2464. Min Range: -4.2464

Max Act: 4.0694. Min Act: -0.1700

Data Index: 4351199 (Open Web Text)

Max Activating Token Index: 532

Text #7

Max Range: 4.2464. Min Range: -4.2464

Max Act: 4.0806. Min Act: -0.1700

Data Index: 5640792 (Open Web Text)

Max Activating Token Index: 46

Text #8

Max Range: 4.2464. Min Range: -4.2464

Max Act: 4.0789. Min Act: -0.1700

Data Index: 3611346 (Open Web Text)

Max Activating Token Index: 621

Text #9

Max Range: 4.2464. Min Range: -4.2464

Max Act: 4.0409. Min Act: -0.1700

Data Index: 4645959 (Open Web Text)

Max Activating Token Index: 271

Text #10

Max Range: 4.2464. Min Range: -4.2464

Max Act: 4.0255. Min Act: -0.1700

Data Index: 6912659 (Open Web Text)

Max Activating Token Index: 67

Text #11

Max Range: 4.2464. Min Range: -4.2464

Max Act: 4.0175. Min Act: -0.1700

Data Index: 3697234 (Open Web Text)

Max Activating Token Index: 766

Text #12

Max Range: 4.2464. Min Range: -4.2464

Max Act: 4.0084. Min Act: -0.1700

Data Index: 7206311 (Open Web Text)

Max Activating Token Index: 960

Text #13

Max Range: 4.2464. Min Range: -4.2464

Max Act: 4.0069. Min Act: -0.1700

Data Index: 3247736 (Open Web Text)

Max Activating Token Index: 601

Text #14

Max Range: 4.2464. Min Range: -4.2464

Max Act: 3.9989. Min Act: -0.1700

Data Index: 8787236 (Open Web Text)

Max Activating Token Index: 175

Text #15

Max Range: 4.2464. Min Range: -4.2464

Max Act: 3.9926. Min Act: -0.1700

Data Index: 8717777 (Open Web Text)

Max Activating Token Index: 609

Text #16

Max Range: 4.2464. Min Range: -4.2464

Max Act: 3.9803. Min Act: -0.1700

Data Index: 2431628 (Open Web Text)

Max Activating Token Index: 912

Text #17

Max Range: 4.2464. Min Range: -4.2464

Max Act: 3.9711. Min Act: -0.1700

Data Index: 7249761 (Open Web Text)

Max Activating Token Index: 470

Text #18

Max Range: 4.2464. Min Range: -4.2464

Max Act: 4.0057. Min Act: -0.1700

Data Index: 1533094 (Open Web Text)

Max Activating Token Index: 513

Text #19

Max Range: 4.2464. Min Range: -4.2464

Max Act: 3.9781. Min Act: -0.1700

Data Index: 5082674 (Open Web Text)

Max Activating Token Index: 685