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

Dataset: Open Web Text

Neuron 2984 in Layer 1

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: 4.0602. Min Range: -4.0602

Max Act: 4.0602. Min Act: -0.1700

Data Index: 3459341 (Open Web Text)

Max Activating Token Index: 20

Text #1

Max Range: 4.0602. Min Range: -4.0602

Max Act: 3.9483. Min Act: -0.1700

Data Index: 6306930 (Open Web Text)

Max Activating Token Index: 395

Text #2

Max Range: 4.0602. Min Range: -4.0602

Max Act: 3.9252. Min Act: -0.1700

Data Index: 7663897 (Open Web Text)

Max Activating Token Index: 770

Text #3

Max Range: 4.0602. Min Range: -4.0602

Max Act: 3.9216. Min Act: -0.1700

Data Index: 3660571 (Open Web Text)

Max Activating Token Index: 15

Text #4

Max Range: 4.0602. Min Range: -4.0602

Max Act: 3.9203. Min Act: -0.1700

Data Index: 5248008 (Open Web Text)

Max Activating Token Index: 491

Text #5

Max Range: 4.0602. Min Range: -4.0602

Max Act: 3.8875. Min Act: -0.1700

Data Index: 7845026 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.0602. Min Range: -4.0602

Max Act: 3.8831. Min Act: -0.1700

Data Index: 5269280 (Open Web Text)

Max Activating Token Index: 396

Text #7

Max Range: 4.0602. Min Range: -4.0602

Max Act: 3.8681. Min Act: -0.1700

Data Index: 8409566 (Open Web Text)

Max Activating Token Index: 558

Text #8

Max Range: 4.0602. Min Range: -4.0602

Max Act: 3.8726. Min Act: -0.1700

Data Index: 1501922 (Open Web Text)

Max Activating Token Index: 381

Text #9

Max Range: 4.0602. Min Range: -4.0602

Max Act: 3.8847. Min Act: -0.1700

Data Index: 4757026 (Open Web Text)

Max Activating Token Index: 531

Text #10

Max Range: 4.0602. Min Range: -4.0602

Max Act: 3.8735. Min Act: -0.1700

Data Index: 4754601 (Open Web Text)

Max Activating Token Index: 16

Text #11

Max Range: 4.0602. Min Range: -4.0602

Max Act: 3.8912. Min Act: -0.1700

Data Index: 4464112 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 4.0602. Min Range: -4.0602

Max Act: 3.8663. Min Act: -0.1700

Data Index: 3048600 (Open Web Text)

Max Activating Token Index: 137

Text #13

Max Range: 4.0602. Min Range: -4.0602

Max Act: 3.8544. Min Act: -0.1700

Data Index: 2876344 (Open Web Text)

Max Activating Token Index: 458

Text #14

Max Range: 4.0602. Min Range: -4.0602

Max Act: 3.8579. Min Act: -0.1700

Data Index: 1800287 (Open Web Text)

Max Activating Token Index: 681

Text #15

Max Range: 4.0602. Min Range: -4.0602

Max Act: 3.8467. Min Act: -0.1700

Data Index: 3241751 (Open Web Text)

Max Activating Token Index: 21

Text #16

Max Range: 4.0602. Min Range: -4.0602

Max Act: 3.8383. Min Act: -0.1700

Data Index: 8138610 (Open Web Text)

Max Activating Token Index: 597

Text #17

Max Range: 4.0602. Min Range: -4.0602

Max Act: 3.8393. Min Act: -0.1700

Data Index: 7253656 (Open Web Text)

Max Activating Token Index: 540

Text #18

Max Range: 4.0602. Min Range: -4.0602

Max Act: 3.8449. Min Act: -0.1700

Data Index: 1816096 (Open Web Text)

Max Activating Token Index: 744

Text #19

Max Range: 4.0602. Min Range: -4.0602

Max Act: 3.8627. Min Act: -0.1700

Data Index: 8266417 (Open Web Text)

Max Activating Token Index: 3