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

Dataset: Open Web Text

Neuron 1397 in Layer 6

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: 3.6395. Min Range: -3.6395

Max Act: 3.6278. Min Act: -0.1700

Data Index: 2443207 (Open Web Text)

Max Activating Token Index: 597

Text #1

Max Range: 3.6395. Min Range: -3.6395

Max Act: 3.6395. Min Act: -0.1700

Data Index: 2510161 (Open Web Text)

Max Activating Token Index: 504

Text #2

Max Range: 3.6395. Min Range: -3.6395

Max Act: 3.5717. Min Act: -0.1700

Data Index: 3720898 (Open Web Text)

Max Activating Token Index: 410

Text #3

Max Range: 3.6395. Min Range: -3.6395

Max Act: 3.5513. Min Act: -0.1700

Data Index: 3410712 (Open Web Text)

Max Activating Token Index: 631

Text #4

Max Range: 3.6395. Min Range: -3.6395

Max Act: 3.5375. Min Act: -0.1700

Data Index: 4176690 (Open Web Text)

Max Activating Token Index: 269

Text #5

Max Range: 3.6395. Min Range: -3.6395

Max Act: 3.5542. Min Act: -0.1700

Data Index: 468564 (Open Web Text)

Max Activating Token Index: 44

Text #6

Max Range: 3.6395. Min Range: -3.6395

Max Act: 3.5176. Min Act: -0.1700

Data Index: 1160268 (Open Web Text)

Max Activating Token Index: 397

Text #7

Max Range: 3.6395. Min Range: -3.6395

Max Act: 3.4908. Min Act: -0.1700

Data Index: 654278 (Open Web Text)

Max Activating Token Index: 282

Text #8

Max Range: 3.6395. Min Range: -3.6395

Max Act: 3.5083. Min Act: -0.1700

Data Index: 1029645 (Open Web Text)

Max Activating Token Index: 487

Text #9

Max Range: 3.6395. Min Range: -3.6395

Max Act: 3.5086. Min Act: -0.1700

Data Index: 8504641 (Open Web Text)

Max Activating Token Index: 691

Text #10

Max Range: 3.6395. Min Range: -3.6395

Max Act: 3.5125. Min Act: -0.1700

Data Index: 8183192 (Open Web Text)

Max Activating Token Index: 960

Text #11

Max Range: 3.6395. Min Range: -3.6395

Max Act: 3.5095. Min Act: -0.1700

Data Index: 4582381 (Open Web Text)

Max Activating Token Index: 949

Text #12

Max Range: 3.6395. Min Range: -3.6395

Max Act: 3.4735. Min Act: -0.1700

Data Index: 299480 (Open Web Text)

Max Activating Token Index: 382

Text #13

Max Range: 3.6395. Min Range: -3.6395

Max Act: 3.4760. Min Act: -0.1700

Data Index: 6925434 (Open Web Text)

Max Activating Token Index: 119

Text #14

Max Range: 3.6395. Min Range: -3.6395

Max Act: 3.4743. Min Act: -0.1700

Data Index: 6457745 (Open Web Text)

Max Activating Token Index: 85

Text #15

Max Range: 3.6395. Min Range: -3.6395

Max Act: 3.4906. Min Act: -0.1700

Data Index: 11218 (Open Web Text)

Max Activating Token Index: 96

Text #16

Max Range: 3.6395. Min Range: -3.6395

Max Act: 3.5027. Min Act: -0.1700

Data Index: 527330 (Open Web Text)

Max Activating Token Index: 590

Text #17

Max Range: 3.6395. Min Range: -3.6395

Max Act: 3.4723. Min Act: -0.1700

Data Index: 8046791 (Open Web Text)

Max Activating Token Index: 410

Text #18

Max Range: 3.6395. Min Range: -3.6395

Max Act: 3.4758. Min Act: -0.1700

Data Index: 7109102 (Open Web Text)

Max Activating Token Index: 656

Text #19

Max Range: 3.6395. Min Range: -3.6395

Max Act: 3.4710. Min Act: -0.1700

Data Index: 1236788 (Open Web Text)

Max Activating Token Index: 633