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

Dataset: Open Web Text

Neuron 1005 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: 4.4527. Min Range: -4.4527

Max Act: 4.4527. Min Act: -0.1700

Data Index: 3313618 (Open Web Text)

Max Activating Token Index: 838

Text #1

Max Range: 4.4527. Min Range: -4.4527

Max Act: 4.4022. Min Act: -0.1700

Data Index: 6945563 (Open Web Text)

Max Activating Token Index: 57

Text #2

Max Range: 4.4527. Min Range: -4.4527

Max Act: 4.3983. Min Act: -0.1700

Data Index: 1401639 (Open Web Text)

Max Activating Token Index: 406

Text #3

Max Range: 4.4527. Min Range: -4.4527

Max Act: 4.3752. Min Act: -0.1700

Data Index: 7782580 (Open Web Text)

Max Activating Token Index: 231

Text #4

Max Range: 4.4527. Min Range: -4.4527

Max Act: 4.3696. Min Act: -0.1700

Data Index: 5908919 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.4527. Min Range: -4.4527

Max Act: 4.3602. Min Act: -0.1700

Data Index: 7929485 (Open Web Text)

Max Activating Token Index: 761

Text #6

Max Range: 4.4527. Min Range: -4.4527

Max Act: 4.3634. Min Act: -0.1700

Data Index: 7525633 (Open Web Text)

Max Activating Token Index: 945

Text #7

Max Range: 4.4527. Min Range: -4.4527

Max Act: 4.3159. Min Act: -0.1700

Data Index: 788614 (Open Web Text)

Max Activating Token Index: 32

Text #8

Max Range: 4.4527. Min Range: -4.4527

Max Act: 4.3530. Min Act: -0.1700

Data Index: 6615627 (Open Web Text)

Max Activating Token Index: 446

Text #9

Max Range: 4.4527. Min Range: -4.4527

Max Act: 4.3712. Min Act: -0.1700

Data Index: 4300949 (Open Web Text)

Max Activating Token Index: 148

Text #10

Max Range: 4.4527. Min Range: -4.4527

Max Act: 4.3207. Min Act: -0.1700

Data Index: 4308170 (Open Web Text)

Max Activating Token Index: 211

Text #11

Max Range: 4.4527. Min Range: -4.4527

Max Act: 4.3067. Min Act: -0.1700

Data Index: 47406 (Open Web Text)

Max Activating Token Index: 437

Text #12

Max Range: 4.4527. Min Range: -4.4527

Max Act: 4.2782. Min Act: -0.1700

Data Index: 2153795 (Open Web Text)

Max Activating Token Index: 34

Text #13

Max Range: 4.4527. Min Range: -4.4527

Max Act: 4.2895. Min Act: -0.1700

Data Index: 4624062 (Open Web Text)

Max Activating Token Index: 517

Text #14

Max Range: 4.4527. Min Range: -4.4527

Max Act: 4.2826. Min Act: -0.1700

Data Index: 7823799 (Open Web Text)

Max Activating Token Index: 589

Text #15

Max Range: 4.4527. Min Range: -4.4527

Max Act: 4.2728. Min Act: -0.1700

Data Index: 5384068 (Open Web Text)

Max Activating Token Index: 57

Text #16

Max Range: 4.4527. Min Range: -4.4527

Max Act: 4.2881. Min Act: -0.1700

Data Index: 7980391 (Open Web Text)

Max Activating Token Index: 904

Text #17

Max Range: 4.4527. Min Range: -4.4527

Max Act: 4.2812. Min Act: -0.1700

Data Index: 2617559 (Open Web Text)

Max Activating Token Index: 771

Text #18

Max Range: 4.4527. Min Range: -4.4527

Max Act: 4.2789. Min Act: -0.1700

Data Index: 13733 (Open Web Text)

Max Activating Token Index: 556

Text #19

Max Range: 4.4527. Min Range: -4.4527

Max Act: 4.2774. Min Act: -0.1700

Data Index: 5937541 (Open Web Text)

Max Activating Token Index: 41