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

Dataset: Open Web Text

Neuron 1617 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: 4.6479. Min Range: -4.6479

Max Act: 4.6479. Min Act: -0.1700

Data Index: 5314710 (Open Web Text)

Max Activating Token Index: 800

Text #1

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.4787. Min Act: -0.1700

Data Index: 3116698 (Open Web Text)

Max Activating Token Index: 508

Text #2

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.4658. Min Act: -0.1700

Data Index: 1057862 (Open Web Text)

Max Activating Token Index: 88

Text #3

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.4541. Min Act: -0.1700

Data Index: 761631 (Open Web Text)

Max Activating Token Index: 542

Text #4

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.4179. Min Act: -0.1700

Data Index: 8659132 (Open Web Text)

Max Activating Token Index: 958

Text #5

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.4239. Min Act: -0.1700

Data Index: 702515 (Open Web Text)

Max Activating Token Index: 577

Text #6

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.4043. Min Act: -0.1700

Data Index: 1622880 (Open Web Text)

Max Activating Token Index: 681

Text #7

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.3973. Min Act: -0.1700

Data Index: 843126 (Open Web Text)

Max Activating Token Index: 752

Text #8

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.3472. Min Act: -0.1700

Data Index: 4039956 (Open Web Text)

Max Activating Token Index: 516

Text #9

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.3823. Min Act: -0.1700

Data Index: 1956329 (Open Web Text)

Max Activating Token Index: 466

Text #10

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.3685. Min Act: -0.1700

Data Index: 365595 (Open Web Text)

Max Activating Token Index: 341

Text #11

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.3758. Min Act: -0.1700

Data Index: 735522 (Open Web Text)

Max Activating Token Index: 965

Text #12

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.3328. Min Act: -0.1700

Data Index: 579476 (Open Web Text)

Max Activating Token Index: 959

Text #13

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.3269. Min Act: -0.1700

Data Index: 6765457 (Open Web Text)

Max Activating Token Index: 397

Text #14

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.3352. Min Act: -0.1700

Data Index: 1219395 (Open Web Text)

Max Activating Token Index: 762

Text #15

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.3431. Min Act: -0.1700

Data Index: 5276951 (Open Web Text)

Max Activating Token Index: 950

Text #16

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.3154. Min Act: -0.1700

Data Index: 3536116 (Open Web Text)

Max Activating Token Index: 522

Text #17

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.3296. Min Act: -0.1700

Data Index: 5137282 (Open Web Text)

Max Activating Token Index: 231

Text #18

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.3180. Min Act: -0.1700

Data Index: 4949132 (Open Web Text)

Max Activating Token Index: 1022

Text #19

Max Range: 4.6479. Min Range: -4.6479

Max Act: 4.2910. Min Act: -0.1700

Data Index: 1173019 (Open Web Text)

Max Activating Token Index: 138