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

Dataset: Open Web Text

Neuron 1396 in Layer 1

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: 3.0984. Min Range: -3.0984

Max Act: 3.0984. Min Act: -0.1700

Data Index: 8582999 (Open Web Text)

Max Activating Token Index: 549

Text #1

Max Range: 3.0984. Min Range: -3.0984

Max Act: 3.0722. Min Act: -0.1700

Data Index: 8627218 (Open Web Text)

Max Activating Token Index: 183

Text #2

Max Range: 3.0984. Min Range: -3.0984

Max Act: 3.0429. Min Act: -0.1700

Data Index: 2894314 (Open Web Text)

Max Activating Token Index: 502

Text #3

Max Range: 3.0984. Min Range: -3.0984

Max Act: 3.0465. Min Act: -0.1700

Data Index: 8032493 (Open Web Text)

Max Activating Token Index: 71

Text #4

Max Range: 3.0984. Min Range: -3.0984

Max Act: 2.9930. Min Act: -0.1700

Data Index: 7849201 (Open Web Text)

Max Activating Token Index: 356

Text #5

Max Range: 3.0984. Min Range: -3.0984

Max Act: 3.0084. Min Act: -0.1700

Data Index: 3374816 (Open Web Text)

Max Activating Token Index: 40

Text #6

Max Range: 3.0984. Min Range: -3.0984

Max Act: 2.9998. Min Act: -0.1700

Data Index: 3352781 (Open Web Text)

Max Activating Token Index: 58

Text #7

Max Range: 3.0984. Min Range: -3.0984

Max Act: 3.0085. Min Act: -0.1700

Data Index: 6045883 (Open Web Text)

Max Activating Token Index: 518

Text #8

Max Range: 3.0984. Min Range: -3.0984

Max Act: 3.0021. Min Act: -0.1700

Data Index: 27656 (Open Web Text)

Max Activating Token Index: 428

Text #9

Max Range: 3.0984. Min Range: -3.0984

Max Act: 2.9927. Min Act: -0.1700

Data Index: 5964515 (Open Web Text)

Max Activating Token Index: 413

Text #10

Max Range: 3.0984. Min Range: -3.0984

Max Act: 3.0084. Min Act: -0.1700

Data Index: 4714707 (Open Web Text)

Max Activating Token Index: 134

Text #11

Max Range: 3.0984. Min Range: -3.0984

Max Act: 3.0198. Min Act: -0.1700

Data Index: 7657330 (Open Web Text)

Max Activating Token Index: 486

Text #12

Max Range: 3.0984. Min Range: -3.0984

Max Act: 2.9960. Min Act: -0.1700

Data Index: 2684723 (Open Web Text)

Max Activating Token Index: 480

Text #13

Max Range: 3.0984. Min Range: -3.0984

Max Act: 2.9929. Min Act: -0.1700

Data Index: 5666330 (Open Web Text)

Max Activating Token Index: 199

Text #14

Max Range: 3.0984. Min Range: -3.0984

Max Act: 2.9771. Min Act: -0.1700

Data Index: 963982 (Open Web Text)

Max Activating Token Index: 468

Text #15

Max Range: 3.0984. Min Range: -3.0984

Max Act: 2.9951. Min Act: -0.1700

Data Index: 6186766 (Open Web Text)

Max Activating Token Index: 455

Text #16

Max Range: 3.0984. Min Range: -3.0984

Max Act: 2.9868. Min Act: -0.1700

Data Index: 6329311 (Open Web Text)

Max Activating Token Index: 296

Text #17

Max Range: 3.0984. Min Range: -3.0984

Max Act: 2.9837. Min Act: -0.1700

Data Index: 6387888 (Open Web Text)

Max Activating Token Index: 673

Text #18

Max Range: 3.0984. Min Range: -3.0984

Max Act: 2.9875. Min Act: -0.1700

Data Index: 1689708 (Open Web Text)

Max Activating Token Index: 82

Text #19

Max Range: 3.0984. Min Range: -3.0984

Max Act: 2.9776. Min Act: -0.1700

Data Index: 7477525 (Open Web Text)

Max Activating Token Index: 725