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

Dataset: Open Web Text

Neuron 1997 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: 4.6663. Min Range: -4.6663

Max Act: 4.6663. Min Act: -0.1700

Data Index: 1991020 (Open Web Text)

Max Activating Token Index: 661

Text #1

Max Range: 4.6663. Min Range: -4.6663

Max Act: 4.5524. Min Act: -0.1700

Data Index: 5008023 (Open Web Text)

Max Activating Token Index: 352

Text #2

Max Range: 4.6663. Min Range: -4.6663

Max Act: 4.5743. Min Act: -0.1700

Data Index: 2188516 (Open Web Text)

Max Activating Token Index: 373

Text #3

Max Range: 4.6663. Min Range: -4.6663

Max Act: 4.5569. Min Act: -0.1700

Data Index: 1991026 (Open Web Text)

Max Activating Token Index: 403

Text #4

Max Range: 4.6663. Min Range: -4.6663

Max Act: 4.4132. Min Act: -0.1700

Data Index: 5667525 (Open Web Text)

Max Activating Token Index: 406

Text #5

Max Range: 4.6663. Min Range: -4.6663

Max Act: 4.4400. Min Act: -0.1700

Data Index: 1719231 (Open Web Text)

Max Activating Token Index: 226

Text #6

Max Range: 4.6663. Min Range: -4.6663

Max Act: 4.4457. Min Act: -0.1700

Data Index: 5008011 (Open Web Text)

Max Activating Token Index: 634

Text #7

Max Range: 4.6663. Min Range: -4.6663

Max Act: 4.4079. Min Act: -0.1700

Data Index: 1719239 (Open Web Text)

Max Activating Token Index: 396

Text #8

Max Range: 4.6663. Min Range: -4.6663

Max Act: 4.3595. Min Act: -0.1700

Data Index: 2188511 (Open Web Text)

Max Activating Token Index: 404

Text #9

Max Range: 4.6663. Min Range: -4.6663

Max Act: 4.3564. Min Act: -0.1700

Data Index: 8671702 (Open Web Text)

Max Activating Token Index: 261

Text #10

Max Range: 4.6663. Min Range: -4.6663

Max Act: 4.3622. Min Act: -0.1700

Data Index: 3561831 (Open Web Text)

Max Activating Token Index: 530

Text #11

Max Range: 4.6663. Min Range: -4.6663

Max Act: 4.2875. Min Act: -0.1700

Data Index: 1991021 (Open Web Text)

Max Activating Token Index: 512

Text #12

Max Range: 4.6663. Min Range: -4.6663

Max Act: 4.2749. Min Act: -0.1700

Data Index: 335629 (Open Web Text)

Max Activating Token Index: 404

Text #13

Max Range: 4.6663. Min Range: -4.6663

Max Act: 4.2301. Min Act: -0.1700

Data Index: 2188506 (Open Web Text)

Max Activating Token Index: 916

Text #14

Max Range: 4.6663. Min Range: -4.6663

Max Act: 4.2416. Min Act: -0.1700

Data Index: 5669656 (Open Web Text)

Max Activating Token Index: 498

Text #15

Max Range: 4.6663. Min Range: -4.6663

Max Act: 4.2329. Min Act: -0.1700

Data Index: 1090092 (Open Web Text)

Max Activating Token Index: 428

Text #16

Max Range: 4.6663. Min Range: -4.6663

Max Act: 4.2428. Min Act: -0.1700

Data Index: 1090076 (Open Web Text)

Max Activating Token Index: 148

Text #17

Max Range: 4.6663. Min Range: -4.6663

Max Act: 4.2216. Min Act: -0.1700

Data Index: 5008021 (Open Web Text)

Max Activating Token Index: 399

Text #18

Max Range: 4.6663. Min Range: -4.6663

Max Act: 4.2276. Min Act: -0.1700

Data Index: 3561846 (Open Web Text)

Max Activating Token Index: 347

Text #19

Max Range: 4.6663. Min Range: -4.6663

Max Act: 4.1865. Min Act: -0.1700

Data Index: 1991016 (Open Web Text)

Max Activating Token Index: 344