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

Dataset: Open Web Text

Neuron 1504 in Layer 5

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: 4.2937. Min Range: -4.2937

Max Act: 4.2937. Min Act: -0.1700

Data Index: 893720 (Open Web Text)

Max Activating Token Index: 366

Text #1

Max Range: 4.2937. Min Range: -4.2937

Max Act: 4.2621. Min Act: -0.1700

Data Index: 3526907 (Open Web Text)

Max Activating Token Index: 221

Text #2

Max Range: 4.2937. Min Range: -4.2937

Max Act: 4.2467. Min Act: -0.1700

Data Index: 4803678 (Open Web Text)

Max Activating Token Index: 846

Text #3

Max Range: 4.2937. Min Range: -4.2937

Max Act: 4.2321. Min Act: -0.1700

Data Index: 4150447 (Open Web Text)

Max Activating Token Index: 609

Text #4

Max Range: 4.2937. Min Range: -4.2937

Max Act: 4.2059. Min Act: -0.1700

Data Index: 384906 (Open Web Text)

Max Activating Token Index: 644

Text #5

Max Range: 4.2937. Min Range: -4.2937

Max Act: 4.1925. Min Act: -0.1700

Data Index: 4391329 (Open Web Text)

Max Activating Token Index: 811

Text #6

Max Range: 4.2937. Min Range: -4.2937

Max Act: 4.1483. Min Act: -0.1700

Data Index: 3866561 (Open Web Text)

Max Activating Token Index: 603

Text #7

Max Range: 4.2937. Min Range: -4.2937

Max Act: 4.1357. Min Act: -0.1700

Data Index: 5884174 (Open Web Text)

Max Activating Token Index: 592

Text #8

Max Range: 4.2937. Min Range: -4.2937

Max Act: 4.1182. Min Act: -0.1700

Data Index: 4097693 (Open Web Text)

Max Activating Token Index: 643

Text #9

Max Range: 4.2937. Min Range: -4.2937

Max Act: 4.1333. Min Act: -0.1700

Data Index: 4802051 (Open Web Text)

Max Activating Token Index: 639

Text #10

Max Range: 4.2937. Min Range: -4.2937

Max Act: 4.1282. Min Act: -0.1700

Data Index: 410887 (Open Web Text)

Max Activating Token Index: 977

Text #11

Max Range: 4.2937. Min Range: -4.2937

Max Act: 4.1486. Min Act: -0.1700

Data Index: 8284706 (Open Web Text)

Max Activating Token Index: 527

Text #12

Max Range: 4.2937. Min Range: -4.2937

Max Act: 4.1527. Min Act: -0.1700

Data Index: 512548 (Open Web Text)

Max Activating Token Index: 899

Text #13

Max Range: 4.2937. Min Range: -4.2937

Max Act: 4.1259. Min Act: -0.1700

Data Index: 2936132 (Open Web Text)

Max Activating Token Index: 463

Text #14

Max Range: 4.2937. Min Range: -4.2937

Max Act: 4.1428. Min Act: -0.1700

Data Index: 6692766 (Open Web Text)

Max Activating Token Index: 643

Text #15

Max Range: 4.2937. Min Range: -4.2937

Max Act: 4.1483. Min Act: -0.1700

Data Index: 4967663 (Open Web Text)

Max Activating Token Index: 250

Text #16

Max Range: 4.2937. Min Range: -4.2937

Max Act: 4.0968. Min Act: -0.1700

Data Index: 3545387 (Open Web Text)

Max Activating Token Index: 370

Text #17

Max Range: 4.2937. Min Range: -4.2937

Max Act: 4.0996. Min Act: -0.1700

Data Index: 2311596 (Open Web Text)

Max Activating Token Index: 533

Text #18

Max Range: 4.2937. Min Range: -4.2937

Max Act: 4.1153. Min Act: -0.1700

Data Index: 4693719 (Open Web Text)

Max Activating Token Index: 424

Text #19

Max Range: 4.2937. Min Range: -4.2937

Max Act: 4.0976. Min Act: -0.1700

Data Index: 614544 (Open Web Text)

Max Activating Token Index: 959