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

Dataset: Open Web Text

Neuron 1980 in Layer 5

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: 3.1418. Min Range: -3.1418

Max Act: 3.1418. Min Act: -0.1700

Data Index: 7397461 (Open Web Text)

Max Activating Token Index: 519

Text #1

Max Range: 3.1418. Min Range: -3.1418

Max Act: 3.0177. Min Act: -0.1700

Data Index: 345125 (Open Web Text)

Max Activating Token Index: 90

Text #2

Max Range: 3.1418. Min Range: -3.1418

Max Act: 2.9883. Min Act: -0.1700

Data Index: 6445540 (Open Web Text)

Max Activating Token Index: 534

Text #3

Max Range: 3.1418. Min Range: -3.1418

Max Act: 3.0092. Min Act: -0.1700

Data Index: 5135966 (Open Web Text)

Max Activating Token Index: 669

Text #4

Max Range: 3.1418. Min Range: -3.1418

Max Act: 2.9900. Min Act: -0.1700

Data Index: 4570746 (Open Web Text)

Max Activating Token Index: 68

Text #5

Max Range: 3.1418. Min Range: -3.1418

Max Act: 2.9440. Min Act: -0.1700

Data Index: 1907401 (Open Web Text)

Max Activating Token Index: 388

Text #6

Max Range: 3.1418. Min Range: -3.1418

Max Act: 2.9905. Min Act: -0.1700

Data Index: 4011134 (Open Web Text)

Max Activating Token Index: 794

Text #7

Max Range: 3.1418. Min Range: -3.1418

Max Act: 2.9497. Min Act: -0.1700

Data Index: 670250 (Open Web Text)

Max Activating Token Index: 347

Text #8

Max Range: 3.1418. Min Range: -3.1418

Max Act: 2.9371. Min Act: -0.1700

Data Index: 4130111 (Open Web Text)

Max Activating Token Index: 636

Text #9

Max Range: 3.1418. Min Range: -3.1418

Max Act: 2.9366. Min Act: -0.1700

Data Index: 8362210 (Open Web Text)

Max Activating Token Index: 634

Text #10

Max Range: 3.1418. Min Range: -3.1418

Max Act: 2.9329. Min Act: -0.1700

Data Index: 5677434 (Open Web Text)

Max Activating Token Index: 61

Text #11

Max Range: 3.1418. Min Range: -3.1418

Max Act: 2.9226. Min Act: -0.1700

Data Index: 8084598 (Open Web Text)

Max Activating Token Index: 631

Text #12

Max Range: 3.1418. Min Range: -3.1418

Max Act: 2.9411. Min Act: -0.1700

Data Index: 665682 (Open Web Text)

Max Activating Token Index: 699

Text #13

Max Range: 3.1418. Min Range: -3.1418

Max Act: 2.9212. Min Act: -0.1700

Data Index: 5326013 (Open Web Text)

Max Activating Token Index: 69

Text #14

Max Range: 3.1418. Min Range: -3.1418

Max Act: 2.8995. Min Act: -0.1700

Data Index: 7717541 (Open Web Text)

Max Activating Token Index: 263

Text #15

Max Range: 3.1418. Min Range: -3.1418

Max Act: 2.9104. Min Act: -0.1700

Data Index: 2689499 (Open Web Text)

Max Activating Token Index: 396

Text #16

Max Range: 3.1418. Min Range: -3.1418

Max Act: 2.8993. Min Act: -0.1700

Data Index: 6891416 (Open Web Text)

Max Activating Token Index: 357

Text #17

Max Range: 3.1418. Min Range: -3.1418

Max Act: 2.9043. Min Act: -0.1700

Data Index: 1854684 (Open Web Text)

Max Activating Token Index: 752

Text #18

Max Range: 3.1418. Min Range: -3.1418

Max Act: 2.8950. Min Act: -0.1700

Data Index: 4825149 (Open Web Text)

Max Activating Token Index: 218

Text #19

Max Range: 3.1418. Min Range: -3.1418

Max Act: 2.8951. Min Act: -0.1700

Data Index: 191990 (Open Web Text)

Max Activating Token Index: 29