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

Dataset: Open Web Text

Neuron 904 in Layer 2

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: 3.1151. Min Range: -3.1151

Max Act: 3.1151. Min Act: -0.1700

Data Index: 1103488 (Open Web Text)

Max Activating Token Index: 516

Text #1

Max Range: 3.1151. Min Range: -3.1151

Max Act: 3.0679. Min Act: -0.1700

Data Index: 4365915 (Open Web Text)

Max Activating Token Index: 684

Text #2

Max Range: 3.1151. Min Range: -3.1151

Max Act: 3.0261. Min Act: -0.1700

Data Index: 2505313 (Open Web Text)

Max Activating Token Index: 501

Text #3

Max Range: 3.1151. Min Range: -3.1151

Max Act: 2.9784. Min Act: -0.1700

Data Index: 884026 (Open Web Text)

Max Activating Token Index: 418

Text #4

Max Range: 3.1151. Min Range: -3.1151

Max Act: 3.0073. Min Act: -0.1700

Data Index: 4722457 (Open Web Text)

Max Activating Token Index: 593

Text #5

Max Range: 3.1151. Min Range: -3.1151

Max Act: 2.9834. Min Act: -0.1700

Data Index: 1256795 (Open Web Text)

Max Activating Token Index: 944

Text #6

Max Range: 3.1151. Min Range: -3.1151

Max Act: 2.9740. Min Act: -0.1700

Data Index: 7846269 (Open Web Text)

Max Activating Token Index: 505

Text #7

Max Range: 3.1151. Min Range: -3.1151

Max Act: 2.9488. Min Act: -0.1700

Data Index: 8522634 (Open Web Text)

Max Activating Token Index: 994

Text #8

Max Range: 3.1151. Min Range: -3.1151

Max Act: 2.9672. Min Act: -0.1700

Data Index: 6563332 (Open Web Text)

Max Activating Token Index: 465

Text #9

Max Range: 3.1151. Min Range: -3.1151

Max Act: 2.9624. Min Act: -0.1700

Data Index: 792632 (Open Web Text)

Max Activating Token Index: 666

Text #10

Max Range: 3.1151. Min Range: -3.1151

Max Act: 2.9557. Min Act: -0.1700

Data Index: 4023301 (Open Web Text)

Max Activating Token Index: 532

Text #11

Max Range: 3.1151. Min Range: -3.1151

Max Act: 2.9719. Min Act: -0.1700

Data Index: 5864646 (Open Web Text)

Max Activating Token Index: 565

Text #12

Max Range: 3.1151. Min Range: -3.1151

Max Act: 2.9797. Min Act: -0.1700

Data Index: 5382668 (Open Web Text)

Max Activating Token Index: 1006

Text #13

Max Range: 3.1151. Min Range: -3.1151

Max Act: 2.9778. Min Act: -0.1700

Data Index: 2091708 (Open Web Text)

Max Activating Token Index: 517

Text #14

Max Range: 3.1151. Min Range: -3.1151

Max Act: 2.9695. Min Act: -0.1700

Data Index: 688189 (Open Web Text)

Max Activating Token Index: 470

Text #15

Max Range: 3.1151. Min Range: -3.1151

Max Act: 2.9652. Min Act: -0.1700

Data Index: 887334 (Open Web Text)

Max Activating Token Index: 170

Text #16

Max Range: 3.1151. Min Range: -3.1151

Max Act: 2.9347. Min Act: -0.1700

Data Index: 1512985 (Open Web Text)

Max Activating Token Index: 524

Text #17

Max Range: 3.1151. Min Range: -3.1151

Max Act: 2.9642. Min Act: -0.1700

Data Index: 3868192 (Open Web Text)

Max Activating Token Index: 537

Text #18

Max Range: 3.1151. Min Range: -3.1151

Max Act: 2.9418. Min Act: -0.1700

Data Index: 530352 (Open Web Text)

Max Activating Token Index: 277

Text #19

Max Range: 3.1151. Min Range: -3.1151

Max Act: 2.9485. Min Act: -0.1700

Data Index: 4144072 (Open Web Text)

Max Activating Token Index: 605