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

Dataset: Open Web Text

Neuron 1175 in Layer 2

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: 1.8954. Min Range: -1.8954

Max Act: 1.8954. Min Act: -0.1700

Data Index: 6116007 (Open Web Text)

Max Activating Token Index: 525

Text #1

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.8893. Min Act: -0.1700

Data Index: 5064342 (Open Web Text)

Max Activating Token Index: 365

Text #2

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.8804. Min Act: -0.1700

Data Index: 4431860 (Open Web Text)

Max Activating Token Index: 760

Text #3

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.8901. Min Act: -0.1700

Data Index: 7436502 (Open Web Text)

Max Activating Token Index: 424

Text #4

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.8759. Min Act: -0.1700

Data Index: 4325954 (Open Web Text)

Max Activating Token Index: 311

Text #5

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.8845. Min Act: -0.1700

Data Index: 3936511 (Open Web Text)

Max Activating Token Index: 643

Text #6

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.8663. Min Act: -0.1700

Data Index: 6205221 (Open Web Text)

Max Activating Token Index: 337

Text #7

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.8701. Min Act: -0.1700

Data Index: 7054434 (Open Web Text)

Max Activating Token Index: 473

Text #8

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.8628. Min Act: -0.1700

Data Index: 4678292 (Open Web Text)

Max Activating Token Index: 265

Text #9

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.8663. Min Act: -0.1700

Data Index: 7337302 (Open Web Text)

Max Activating Token Index: 276

Text #10

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.8553. Min Act: -0.1700

Data Index: 1045959 (Open Web Text)

Max Activating Token Index: 711

Text #11

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.8557. Min Act: -0.1700

Data Index: 3087818 (Open Web Text)

Max Activating Token Index: 397

Text #12

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.8603. Min Act: -0.1700

Data Index: 8753025 (Open Web Text)

Max Activating Token Index: 399

Text #13

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.8489. Min Act: -0.1700

Data Index: 3681228 (Open Web Text)

Max Activating Token Index: 577

Text #14

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.8451. Min Act: -0.1700

Data Index: 2714022 (Open Web Text)

Max Activating Token Index: 489

Text #15

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.8520. Min Act: -0.1700

Data Index: 934082 (Open Web Text)

Max Activating Token Index: 350

Text #16

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.8477. Min Act: -0.1700

Data Index: 7746371 (Open Web Text)

Max Activating Token Index: 705

Text #17

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.8478. Min Act: -0.1700

Data Index: 2603473 (Open Web Text)

Max Activating Token Index: 21

Text #18

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.8496. Min Act: -0.1700

Data Index: 1149248 (Open Web Text)

Max Activating Token Index: 285

Text #19

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.8510. Min Act: -0.1700

Data Index: 1458091 (Open Web Text)

Max Activating Token Index: 456