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

Dataset: Open Web Text

Neuron 604 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: 1.6817. Min Range: -1.6817

Max Act: 1.6817. Min Act: -0.1700

Data Index: 2892784 (Open Web Text)

Max Activating Token Index: 448

Text #1

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.6759. Min Act: -0.1700

Data Index: 4892404 (Open Web Text)

Max Activating Token Index: 746

Text #2

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.6532. Min Act: -0.1700

Data Index: 8638531 (Open Web Text)

Max Activating Token Index: 778

Text #3

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.6390. Min Act: -0.1700

Data Index: 2218348 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.6344. Min Act: -0.1700

Data Index: 6490148 (Open Web Text)

Max Activating Token Index: 374

Text #5

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.6223. Min Act: -0.1700

Data Index: 6015834 (Open Web Text)

Max Activating Token Index: 233

Text #6

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.6080. Min Act: -0.1700

Data Index: 6992000 (Open Web Text)

Max Activating Token Index: 448

Text #7

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.6233. Min Act: -0.1700

Data Index: 5557924 (Open Web Text)

Max Activating Token Index: 835

Text #8

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.6282. Min Act: -0.1700

Data Index: 3553449 (Open Web Text)

Max Activating Token Index: 418

Text #9

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.6202. Min Act: -0.1700

Data Index: 4955035 (Open Web Text)

Max Activating Token Index: 263

Text #10

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.6060. Min Act: -0.1700

Data Index: 2908475 (Open Web Text)

Max Activating Token Index: 369

Text #11

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.6151. Min Act: -0.1700

Data Index: 388532 (Open Web Text)

Max Activating Token Index: 81

Text #12

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.6162. Min Act: -0.1700

Data Index: 2159855 (Open Web Text)

Max Activating Token Index: 97

Text #13

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.6249. Min Act: -0.1700

Data Index: 5591703 (Open Web Text)

Max Activating Token Index: 465

Text #14

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.6111. Min Act: -0.1700

Data Index: 105701 (Open Web Text)

Max Activating Token Index: 698

Text #15

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.6043. Min Act: -0.1700

Data Index: 981635 (Open Web Text)

Max Activating Token Index: 442

Text #16

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.6067. Min Act: -0.1700

Data Index: 3698105 (Open Web Text)

Max Activating Token Index: 852

Text #17

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.5967. Min Act: -0.1700

Data Index: 6379601 (Open Web Text)

Max Activating Token Index: 760

Text #18

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.6025. Min Act: -0.1700

Data Index: 4980457 (Open Web Text)

Max Activating Token Index: 396

Text #19

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.5965. Min Act: -0.1700

Data Index: 4718717 (Open Web Text)

Max Activating Token Index: 453