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

Dataset: Open Web Text

Neuron 1105 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: 5.6620. Min Range: -5.6620

Max Act: 5.6620. Min Act: -0.1700

Data Index: 4714954 (Open Web Text)

Max Activating Token Index: 105

Text #1

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.5967. Min Act: -0.1700

Data Index: 3377875 (Open Web Text)

Max Activating Token Index: 919

Text #2

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.5858. Min Act: -0.1700

Data Index: 6816253 (Open Web Text)

Max Activating Token Index: 388

Text #3

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.5819. Min Act: -0.1700

Data Index: 2394557 (Open Web Text)

Max Activating Token Index: 159

Text #4

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.6012. Min Act: -0.1700

Data Index: 1505634 (Open Web Text)

Max Activating Token Index: 698

Text #5

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.5559. Min Act: -0.1700

Data Index: 7328381 (Open Web Text)

Max Activating Token Index: 440

Text #6

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.5891. Min Act: -0.1700

Data Index: 3236189 (Open Web Text)

Max Activating Token Index: 125

Text #7

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.5331. Min Act: -0.1700

Data Index: 7749771 (Open Web Text)

Max Activating Token Index: 496

Text #8

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.5458. Min Act: -0.1700

Data Index: 3682891 (Open Web Text)

Max Activating Token Index: 698

Text #9

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.5375. Min Act: -0.1700

Data Index: 8756580 (Open Web Text)

Max Activating Token Index: 100

Text #10

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.4976. Min Act: -0.1700

Data Index: 7355921 (Open Web Text)

Max Activating Token Index: 902

Text #11

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.5033. Min Act: -0.1700

Data Index: 248716 (Open Web Text)

Max Activating Token Index: 404

Text #12

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.5045. Min Act: -0.1700

Data Index: 2984639 (Open Web Text)

Max Activating Token Index: 22

Text #13

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.5423. Min Act: -0.1700

Data Index: 7785040 (Open Web Text)

Max Activating Token Index: 153

Text #14

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.4659. Min Act: -0.1700

Data Index: 4994770 (Open Web Text)

Max Activating Token Index: 445

Text #15

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.4630. Min Act: -0.1700

Data Index: 1584609 (Open Web Text)

Max Activating Token Index: 80

Text #16

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.4882. Min Act: -0.1700

Data Index: 5627021 (Open Web Text)

Max Activating Token Index: 870

Text #17

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.4747. Min Act: -0.1700

Data Index: 6603973 (Open Web Text)

Max Activating Token Index: 688

Text #18

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.4950. Min Act: -0.1700

Data Index: 1571120 (Open Web Text)

Max Activating Token Index: 128

Text #19

Max Range: 5.6620. Min Range: -5.6620

Max Act: 5.4911. Min Act: -0.1700

Data Index: 1144010 (Open Web Text)

Max Activating Token Index: 410