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

Dataset: Open Web Text

Neuron 3058 in Layer 4

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: 3.0638. Min Range: -3.0638

Max Act: 3.0638. Min Act: -0.1700

Data Index: 4696205 (Open Web Text)

Max Activating Token Index: 800

Text #1

Max Range: 3.0638. Min Range: -3.0638

Max Act: 2.9043. Min Act: -0.1700

Data Index: 5773807 (Open Web Text)

Max Activating Token Index: 964

Text #2

Max Range: 3.0638. Min Range: -3.0638

Max Act: 2.8440. Min Act: -0.1700

Data Index: 5744416 (Open Web Text)

Max Activating Token Index: 1005

Text #3

Max Range: 3.0638. Min Range: -3.0638

Max Act: 2.8592. Min Act: -0.1700

Data Index: 1305261 (Open Web Text)

Max Activating Token Index: 787

Text #4

Max Range: 3.0638. Min Range: -3.0638

Max Act: 2.8638. Min Act: -0.1700

Data Index: 8464605 (Open Web Text)

Max Activating Token Index: 858

Text #5

Max Range: 3.0638. Min Range: -3.0638

Max Act: 2.8334. Min Act: -0.1700

Data Index: 5241020 (Open Web Text)

Max Activating Token Index: 992

Text #6

Max Range: 3.0638. Min Range: -3.0638

Max Act: 2.8218. Min Act: -0.1700

Data Index: 8269714 (Open Web Text)

Max Activating Token Index: 514

Text #7

Max Range: 3.0638. Min Range: -3.0638

Max Act: 2.8048. Min Act: -0.1700

Data Index: 6798876 (Open Web Text)

Max Activating Token Index: 842

Text #8

Max Range: 3.0638. Min Range: -3.0638

Max Act: 2.7817. Min Act: -0.1700

Data Index: 2545678 (Open Web Text)

Max Activating Token Index: 688

Text #9

Max Range: 3.0638. Min Range: -3.0638

Max Act: 2.7736. Min Act: -0.1700

Data Index: 8425078 (Open Web Text)

Max Activating Token Index: 197

Text #10

Max Range: 3.0638. Min Range: -3.0638

Max Act: 2.7744. Min Act: -0.1700

Data Index: 8539225 (Open Web Text)

Max Activating Token Index: 1004

Text #11

Max Range: 3.0638. Min Range: -3.0638

Max Act: 2.7598. Min Act: -0.1700

Data Index: 4975022 (Open Web Text)

Max Activating Token Index: 572

Text #12

Max Range: 3.0638. Min Range: -3.0638

Max Act: 2.7663. Min Act: -0.1700

Data Index: 2940384 (Open Web Text)

Max Activating Token Index: 415

Text #13

Max Range: 3.0638. Min Range: -3.0638

Max Act: 2.7650. Min Act: -0.1700

Data Index: 8080103 (Open Web Text)

Max Activating Token Index: 508

Text #14

Max Range: 3.0638. Min Range: -3.0638

Max Act: 2.7579. Min Act: -0.1700

Data Index: 1612429 (Open Web Text)

Max Activating Token Index: 976

Text #15

Max Range: 3.0638. Min Range: -3.0638

Max Act: 2.7527. Min Act: -0.1700

Data Index: 3891613 (Open Web Text)

Max Activating Token Index: 538

Text #16

Max Range: 3.0638. Min Range: -3.0638

Max Act: 2.7599. Min Act: -0.1700

Data Index: 8356344 (Open Web Text)

Max Activating Token Index: 566

Text #17

Max Range: 3.0638. Min Range: -3.0638

Max Act: 2.7489. Min Act: -0.1700

Data Index: 7257865 (Open Web Text)

Max Activating Token Index: 198

Text #18

Max Range: 3.0638. Min Range: -3.0638

Max Act: 2.7531. Min Act: -0.1700

Data Index: 523569 (Open Web Text)

Max Activating Token Index: 1004

Text #19

Max Range: 3.0638. Min Range: -3.0638

Max Act: 2.7617. Min Act: -0.1700

Data Index: 8742622 (Open Web Text)

Max Activating Token Index: 363