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

Dataset: Open Web Text

Neuron 2704 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: 5.3313. Min Range: -5.3313

Max Act: 5.3313. Min Act: -0.1700

Data Index: 5487784 (Open Web Text)

Max Activating Token Index: 730

Text #1

Max Range: 5.3313. Min Range: -5.3313

Max Act: 5.1304. Min Act: -0.1700

Data Index: 2802634 (Open Web Text)

Max Activating Token Index: 324

Text #2

Max Range: 5.3313. Min Range: -5.3313

Max Act: 5.0334. Min Act: -0.1700

Data Index: 191639 (Open Web Text)

Max Activating Token Index: 282

Text #3

Max Range: 5.3313. Min Range: -5.3313

Max Act: 5.0411. Min Act: -0.1700

Data Index: 1493921 (Open Web Text)

Max Activating Token Index: 569

Text #4

Max Range: 5.3313. Min Range: -5.3313

Max Act: 5.0160. Min Act: -0.1700

Data Index: 7624113 (Open Web Text)

Max Activating Token Index: 287

Text #5

Max Range: 5.3313. Min Range: -5.3313

Max Act: 5.0291. Min Act: -0.1700

Data Index: 7063775 (Open Web Text)

Max Activating Token Index: 954

Text #6

Max Range: 5.3313. Min Range: -5.3313

Max Act: 4.9787. Min Act: -0.1700

Data Index: 3368161 (Open Web Text)

Max Activating Token Index: 649

Text #7

Max Range: 5.3313. Min Range: -5.3313

Max Act: 4.9684. Min Act: -0.1700

Data Index: 130539 (Open Web Text)

Max Activating Token Index: 699

Text #8

Max Range: 5.3313. Min Range: -5.3313

Max Act: 4.9814. Min Act: -0.1700

Data Index: 5801107 (Open Web Text)

Max Activating Token Index: 211

Text #9

Max Range: 5.3313. Min Range: -5.3313

Max Act: 4.9952. Min Act: -0.1700

Data Index: 6863616 (Open Web Text)

Max Activating Token Index: 1005

Text #10

Max Range: 5.3313. Min Range: -5.3313

Max Act: 4.9728. Min Act: -0.1700

Data Index: 3049250 (Open Web Text)

Max Activating Token Index: 694

Text #11

Max Range: 5.3313. Min Range: -5.3313

Max Act: 4.9368. Min Act: -0.1700

Data Index: 768495 (Open Web Text)

Max Activating Token Index: 668

Text #12

Max Range: 5.3313. Min Range: -5.3313

Max Act: 4.9303. Min Act: -0.1700

Data Index: 8050648 (Open Web Text)

Max Activating Token Index: 601

Text #13

Max Range: 5.3313. Min Range: -5.3313

Max Act: 4.9382. Min Act: -0.1700

Data Index: 2983000 (Open Web Text)

Max Activating Token Index: 121

Text #14

Max Range: 5.3313. Min Range: -5.3313

Max Act: 4.9456. Min Act: -0.1700

Data Index: 4640739 (Open Web Text)

Max Activating Token Index: 798

Text #15

Max Range: 5.3313. Min Range: -5.3313

Max Act: 4.8936. Min Act: -0.1700

Data Index: 584064 (Open Web Text)

Max Activating Token Index: 99

Text #16

Max Range: 5.3313. Min Range: -5.3313

Max Act: 4.9014. Min Act: -0.1700

Data Index: 5172580 (Open Web Text)

Max Activating Token Index: 798

Text #17

Max Range: 5.3313. Min Range: -5.3313

Max Act: 4.8999. Min Act: -0.1700

Data Index: 3382020 (Open Web Text)

Max Activating Token Index: 312

Text #18

Max Range: 5.3313. Min Range: -5.3313

Max Act: 4.8836. Min Act: -0.1700

Data Index: 6276807 (Open Web Text)

Max Activating Token Index: 832

Text #19

Max Range: 5.3313. Min Range: -5.3313

Max Act: 4.8941. Min Act: -0.1700

Data Index: 1195372 (Open Web Text)

Max Activating Token Index: 671