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

Dataset: Open Web Text

Neuron 981 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: 4.2090. Min Range: -4.2090

Max Act: 4.2090. Min Act: -0.1700

Data Index: 6617962 (Open Web Text)

Max Activating Token Index: 626

Text #1

Max Range: 4.2090. Min Range: -4.2090

Max Act: 4.1407. Min Act: -0.1700

Data Index: 7716907 (Open Web Text)

Max Activating Token Index: 379

Text #2

Max Range: 4.2090. Min Range: -4.2090

Max Act: 4.0939. Min Act: -0.1700

Data Index: 8441673 (Open Web Text)

Max Activating Token Index: 80

Text #3

Max Range: 4.2090. Min Range: -4.2090

Max Act: 4.0437. Min Act: -0.1700

Data Index: 7404903 (Open Web Text)

Max Activating Token Index: 979

Text #4

Max Range: 4.2090. Min Range: -4.2090

Max Act: 3.9510. Min Act: -0.1700

Data Index: 3840111 (Open Web Text)

Max Activating Token Index: 753

Text #5

Max Range: 4.2090. Min Range: -4.2090

Max Act: 3.9443. Min Act: -0.1700

Data Index: 2358421 (Open Web Text)

Max Activating Token Index: 225

Text #6

Max Range: 4.2090. Min Range: -4.2090

Max Act: 3.9586. Min Act: -0.1700

Data Index: 1952090 (Open Web Text)

Max Activating Token Index: 782

Text #7

Max Range: 4.2090. Min Range: -4.2090

Max Act: 3.8969. Min Act: -0.1700

Data Index: 4968328 (Open Web Text)

Max Activating Token Index: 442

Text #8

Max Range: 4.2090. Min Range: -4.2090

Max Act: 3.8527. Min Act: -0.1700

Data Index: 4904199 (Open Web Text)

Max Activating Token Index: 743

Text #9

Max Range: 4.2090. Min Range: -4.2090

Max Act: 3.8842. Min Act: -0.1700

Data Index: 7023248 (Open Web Text)

Max Activating Token Index: 329

Text #10

Max Range: 4.2090. Min Range: -4.2090

Max Act: 3.8523. Min Act: -0.1700

Data Index: 3802530 (Open Web Text)

Max Activating Token Index: 559

Text #11

Max Range: 4.2090. Min Range: -4.2090

Max Act: 3.8097. Min Act: -0.1700

Data Index: 8485456 (Open Web Text)

Max Activating Token Index: 799

Text #12

Max Range: 4.2090. Min Range: -4.2090

Max Act: 3.8324. Min Act: -0.1700

Data Index: 424028 (Open Web Text)

Max Activating Token Index: 888

Text #13

Max Range: 4.2090. Min Range: -4.2090

Max Act: 3.7982. Min Act: -0.1700

Data Index: 1191578 (Open Web Text)

Max Activating Token Index: 538

Text #14

Max Range: 4.2090. Min Range: -4.2090

Max Act: 3.7822. Min Act: -0.1700

Data Index: 2751046 (Open Web Text)

Max Activating Token Index: 384

Text #15

Max Range: 4.2090. Min Range: -4.2090

Max Act: 3.7626. Min Act: -0.1700

Data Index: 3596798 (Open Web Text)

Max Activating Token Index: 530

Text #16

Max Range: 4.2090. Min Range: -4.2090

Max Act: 3.7519. Min Act: -0.1700

Data Index: 3508048 (Open Web Text)

Max Activating Token Index: 328

Text #17

Max Range: 4.2090. Min Range: -4.2090

Max Act: 3.7292. Min Act: -0.1700

Data Index: 1069994 (Open Web Text)

Max Activating Token Index: 372

Text #18

Max Range: 4.2090. Min Range: -4.2090

Max Act: 3.7579. Min Act: -0.1700

Data Index: 3208113 (Open Web Text)

Max Activating Token Index: 402

Text #19

Max Range: 4.2090. Min Range: -4.2090

Max Act: 3.7551. Min Act: -0.1700

Data Index: 4774135 (Open Web Text)

Max Activating Token Index: 639