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

Dataset: Open Web Text

Neuron 1194 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: 3.9597. Min Range: -3.9597

Max Act: 3.9597. Min Act: -0.1700

Data Index: 4280107 (Open Web Text)

Max Activating Token Index: 648

Text #1

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.9434. Min Act: -0.1700

Data Index: 4787253 (Open Web Text)

Max Activating Token Index: 345

Text #2

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.9131. Min Act: -0.1700

Data Index: 7844766 (Open Web Text)

Max Activating Token Index: 100

Text #3

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.9159. Min Act: -0.1700

Data Index: 7891944 (Open Web Text)

Max Activating Token Index: 423

Text #4

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.9254. Min Act: -0.1700

Data Index: 8216811 (Open Web Text)

Max Activating Token Index: 197

Text #5

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.9285. Min Act: -0.1700

Data Index: 8614651 (Open Web Text)

Max Activating Token Index: 450

Text #6

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.9147. Min Act: -0.1700

Data Index: 8471692 (Open Web Text)

Max Activating Token Index: 424

Text #7

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.8885. Min Act: -0.1700

Data Index: 5278201 (Open Web Text)

Max Activating Token Index: 610

Text #8

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.9111. Min Act: -0.1700

Data Index: 5426543 (Open Web Text)

Max Activating Token Index: 658

Text #9

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.8837. Min Act: -0.1700

Data Index: 4588388 (Open Web Text)

Max Activating Token Index: 385

Text #10

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.8781. Min Act: -0.1700

Data Index: 207411 (Open Web Text)

Max Activating Token Index: 304

Text #11

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.8504. Min Act: -0.1700

Data Index: 2691439 (Open Web Text)

Max Activating Token Index: 355

Text #12

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.8647. Min Act: -0.1700

Data Index: 2819382 (Open Web Text)

Max Activating Token Index: 635

Text #13

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.8694. Min Act: -0.1700

Data Index: 2655658 (Open Web Text)

Max Activating Token Index: 243

Text #14

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.8586. Min Act: -0.1700

Data Index: 4159389 (Open Web Text)

Max Activating Token Index: 463

Text #15

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.8547. Min Act: -0.1700

Data Index: 2125472 (Open Web Text)

Max Activating Token Index: 142

Text #16

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.8711. Min Act: -0.1700

Data Index: 3197744 (Open Web Text)

Max Activating Token Index: 204

Text #17

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.8800. Min Act: -0.1700

Data Index: 7789627 (Open Web Text)

Max Activating Token Index: 266

Text #18

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.8560. Min Act: -0.1700

Data Index: 6854568 (Open Web Text)

Max Activating Token Index: 609

Text #19

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.8315. Min Act: -0.1700

Data Index: 4512442 (Open Web Text)

Max Activating Token Index: 208