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

Dataset: Open Web Text

Neuron 2207 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: 4.8549. Min Range: -4.8549

Max Act: 4.8549. Min Act: -0.1700

Data Index: 2262612 (Open Web Text)

Max Activating Token Index: 350

Text #1

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.4652. Min Act: -0.1699

Data Index: 658959 (Open Web Text)

Max Activating Token Index: 633

Text #2

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.3757. Min Act: -0.1700

Data Index: 1513508 (Open Web Text)

Max Activating Token Index: 625

Text #3

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.3803. Min Act: -0.1700

Data Index: 7537253 (Open Web Text)

Max Activating Token Index: 500

Text #4

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.3430. Min Act: -0.1700

Data Index: 879350 (Open Web Text)

Max Activating Token Index: 149

Text #5

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.3125. Min Act: -0.1700

Data Index: 7319316 (Open Web Text)

Max Activating Token Index: 627

Text #6

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.3503. Min Act: -0.1700

Data Index: 1581497 (Open Web Text)

Max Activating Token Index: 772

Text #7

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.3542. Min Act: -0.1700

Data Index: 2833777 (Open Web Text)

Max Activating Token Index: 707

Text #8

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.3012. Min Act: -0.1700

Data Index: 5572721 (Open Web Text)

Max Activating Token Index: 970

Text #9

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.2925. Min Act: -0.1700

Data Index: 4555644 (Open Web Text)

Max Activating Token Index: 522

Text #10

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.3260. Min Act: -0.1700

Data Index: 8443569 (Open Web Text)

Max Activating Token Index: 315

Text #11

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.2897. Min Act: -0.1700

Data Index: 6320968 (Open Web Text)

Max Activating Token Index: 376

Text #12

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.3123. Min Act: -0.1700

Data Index: 2183400 (Open Web Text)

Max Activating Token Index: 942

Text #13

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.3663. Min Act: -0.1700

Data Index: 5939996 (Open Web Text)

Max Activating Token Index: 660

Text #14

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.2970. Min Act: -0.1700

Data Index: 7577794 (Open Web Text)

Max Activating Token Index: 206

Text #15

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.2547. Min Act: -0.1700

Data Index: 755972 (Open Web Text)

Max Activating Token Index: 384

Text #16

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.2787. Min Act: -0.1700

Data Index: 4890453 (Open Web Text)

Max Activating Token Index: 819

Text #17

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.2535. Min Act: -0.1700

Data Index: 2113940 (Open Web Text)

Max Activating Token Index: 169

Text #18

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.2915. Min Act: -0.1700

Data Index: 2284904 (Open Web Text)

Max Activating Token Index: 647

Text #19

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.2334. Min Act: -0.1700

Data Index: 5133101 (Open Web Text)

Max Activating Token Index: 513