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

Dataset: Open Web Text

Neuron 1987 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: 4.5467. Min Range: -4.5467

Max Act: 4.5363. Min Act: -0.1700

Data Index: 2969621 (Open Web Text)

Max Activating Token Index: 473

Text #1

Max Range: 4.5467. Min Range: -4.5467

Max Act: 4.5458. Min Act: -0.1700

Data Index: 7707165 (Open Web Text)

Max Activating Token Index: 485

Text #2

Max Range: 4.5467. Min Range: -4.5467

Max Act: 4.5196. Min Act: -0.1700

Data Index: 5654666 (Open Web Text)

Max Activating Token Index: 902

Text #3

Max Range: 4.5467. Min Range: -4.5467

Max Act: 4.5467. Min Act: -0.1700

Data Index: 1782782 (Open Web Text)

Max Activating Token Index: 649

Text #4

Max Range: 4.5467. Min Range: -4.5467

Max Act: 4.4879. Min Act: -0.1700

Data Index: 3677689 (Open Web Text)

Max Activating Token Index: 337

Text #5

Max Range: 4.5467. Min Range: -4.5467

Max Act: 4.4991. Min Act: -0.1700

Data Index: 708410 (Open Web Text)

Max Activating Token Index: 409

Text #6

Max Range: 4.5467. Min Range: -4.5467

Max Act: 4.4758. Min Act: -0.1700

Data Index: 7030224 (Open Web Text)

Max Activating Token Index: 250

Text #7

Max Range: 4.5467. Min Range: -4.5467

Max Act: 4.4191. Min Act: -0.1700

Data Index: 3177686 (Open Web Text)

Max Activating Token Index: 170

Text #8

Max Range: 4.5467. Min Range: -4.5467

Max Act: 4.4372. Min Act: -0.1700

Data Index: 2566640 (Open Web Text)

Max Activating Token Index: 397

Text #9

Max Range: 4.5467. Min Range: -4.5467

Max Act: 4.4410. Min Act: -0.1700

Data Index: 548097 (Open Web Text)

Max Activating Token Index: 414

Text #10

Max Range: 4.5467. Min Range: -4.5467

Max Act: 4.4461. Min Act: -0.1700

Data Index: 5454611 (Open Web Text)

Max Activating Token Index: 81

Text #11

Max Range: 4.5467. Min Range: -4.5467

Max Act: 4.4320. Min Act: -0.1700

Data Index: 1255973 (Open Web Text)

Max Activating Token Index: 357

Text #12

Max Range: 4.5467. Min Range: -4.5467

Max Act: 4.4472. Min Act: -0.1700

Data Index: 201179 (Open Web Text)

Max Activating Token Index: 120

Text #13

Max Range: 4.5467. Min Range: -4.5467

Max Act: 4.4154. Min Act: -0.1700

Data Index: 1649463 (Open Web Text)

Max Activating Token Index: 535

Text #14

Max Range: 4.5467. Min Range: -4.5467

Max Act: 4.4051. Min Act: -0.1700

Data Index: 2532816 (Open Web Text)

Max Activating Token Index: 390

Text #15

Max Range: 4.5467. Min Range: -4.5467

Max Act: 4.3982. Min Act: -0.1700

Data Index: 263947 (Open Web Text)

Max Activating Token Index: 373

Text #16

Max Range: 4.5467. Min Range: -4.5467

Max Act: 4.4088. Min Act: -0.1700

Data Index: 93894 (Open Web Text)

Max Activating Token Index: 432

Text #17

Max Range: 4.5467. Min Range: -4.5467

Max Act: 4.4249. Min Act: -0.1700

Data Index: 5205574 (Open Web Text)

Max Activating Token Index: 530

Text #18

Max Range: 4.5467. Min Range: -4.5467

Max Act: 4.4019. Min Act: -0.1700

Data Index: 1253338 (Open Web Text)

Max Activating Token Index: 354

Text #19

Max Range: 4.5467. Min Range: -4.5467

Max Act: 4.3994. Min Act: -0.1700

Data Index: 73565 (Open Web Text)

Max Activating Token Index: 274