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

Dataset: Open Web Text

Neuron 1363 in Layer 0

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: 4.5434. Min Range: -4.5434

Max Act: 4.5434. Min Act: -0.1700

Data Index: 7294829 (Open Web Text)

Max Activating Token Index: 819

Text #1

Max Range: 4.5434. Min Range: -4.5434

Max Act: 4.4402. Min Act: -0.1700

Data Index: 246205 (Open Web Text)

Max Activating Token Index: 53

Text #2

Max Range: 4.5434. Min Range: -4.5434

Max Act: 4.3948. Min Act: -0.1700

Data Index: 2272356 (Open Web Text)

Max Activating Token Index: 765

Text #3

Max Range: 4.5434. Min Range: -4.5434

Max Act: 4.3633. Min Act: -0.1700

Data Index: 8305754 (Open Web Text)

Max Activating Token Index: 801

Text #4

Max Range: 4.5434. Min Range: -4.5434

Max Act: 4.3685. Min Act: -0.1700

Data Index: 8434058 (Open Web Text)

Max Activating Token Index: 368

Text #5

Max Range: 4.5434. Min Range: -4.5434

Max Act: 4.3413. Min Act: -0.1700

Data Index: 8193205 (Open Web Text)

Max Activating Token Index: 407

Text #6

Max Range: 4.5434. Min Range: -4.5434

Max Act: 4.3214. Min Act: -0.1700

Data Index: 4364467 (Open Web Text)

Max Activating Token Index: 642

Text #7

Max Range: 4.5434. Min Range: -4.5434

Max Act: 4.2969. Min Act: -0.1700

Data Index: 2985747 (Open Web Text)

Max Activating Token Index: 394

Text #8

Max Range: 4.5434. Min Range: -4.5434

Max Act: 4.3070. Min Act: -0.1700

Data Index: 5020803 (Open Web Text)

Max Activating Token Index: 468

Text #9

Max Range: 4.5434. Min Range: -4.5434

Max Act: 4.2816. Min Act: -0.1700

Data Index: 1334688 (Open Web Text)

Max Activating Token Index: 243

Text #10

Max Range: 4.5434. Min Range: -4.5434

Max Act: 4.2803. Min Act: -0.1700

Data Index: 6508435 (Open Web Text)

Max Activating Token Index: 319

Text #11

Max Range: 4.5434. Min Range: -4.5434

Max Act: 4.2765. Min Act: -0.1700

Data Index: 331879 (Open Web Text)

Max Activating Token Index: 385

Text #12

Max Range: 4.5434. Min Range: -4.5434

Max Act: 4.2689. Min Act: -0.1700

Data Index: 8122728 (Open Web Text)

Max Activating Token Index: 430

Text #13

Max Range: 4.5434. Min Range: -4.5434

Max Act: 4.2771. Min Act: -0.1700

Data Index: 3506631 (Open Web Text)

Max Activating Token Index: 235

Text #14

Max Range: 4.5434. Min Range: -4.5434

Max Act: 4.3024. Min Act: -0.1700

Data Index: 4540391 (Open Web Text)

Max Activating Token Index: 762

Text #15

Max Range: 4.5434. Min Range: -4.5434

Max Act: 4.2370. Min Act: -0.1700

Data Index: 6052574 (Open Web Text)

Max Activating Token Index: 138

Text #16

Max Range: 4.5434. Min Range: -4.5434

Max Act: 4.2531. Min Act: -0.1700

Data Index: 285116 (Open Web Text)

Max Activating Token Index: 608

Text #17

Max Range: 4.5434. Min Range: -4.5434

Max Act: 4.2456. Min Act: -0.1700

Data Index: 7657862 (Open Web Text)

Max Activating Token Index: 843

Text #18

Max Range: 4.5434. Min Range: -4.5434

Max Act: 4.2530. Min Act: -0.1700

Data Index: 7906819 (Open Web Text)

Max Activating Token Index: 260

Text #19

Max Range: 4.5434. Min Range: -4.5434

Max Act: 4.2398. Min Act: -0.1700

Data Index: 2034729 (Open Web Text)

Max Activating Token Index: 849