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

Dataset: Open Web Text

Neuron 183 in Layer 3

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: 4.9494. Min Range: -4.9494

Max Act: 4.9494. Min Act: -0.1700

Data Index: 2321600 (Open Web Text)

Max Activating Token Index: 468

Text #1

Max Range: 4.9494. Min Range: -4.9494

Max Act: 4.5946. Min Act: -0.1700

Data Index: 7140585 (Open Web Text)

Max Activating Token Index: 726

Text #2

Max Range: 4.9494. Min Range: -4.9494

Max Act: 4.6025. Min Act: -0.1700

Data Index: 5885707 (Open Web Text)

Max Activating Token Index: 489

Text #3

Max Range: 4.9494. Min Range: -4.9494

Max Act: 4.5670. Min Act: -0.1700

Data Index: 6253213 (Open Web Text)

Max Activating Token Index: 701

Text #4

Max Range: 4.9494. Min Range: -4.9494

Max Act: 4.5445. Min Act: -0.1700

Data Index: 8360503 (Open Web Text)

Max Activating Token Index: 469

Text #5

Max Range: 4.9494. Min Range: -4.9494

Max Act: 4.5589. Min Act: -0.1700

Data Index: 2582718 (Open Web Text)

Max Activating Token Index: 863

Text #6

Max Range: 4.9494. Min Range: -4.9494

Max Act: 4.5592. Min Act: -0.1700

Data Index: 3459794 (Open Web Text)

Max Activating Token Index: 593

Text #7

Max Range: 4.9494. Min Range: -4.9494

Max Act: 4.5544. Min Act: -0.1700

Data Index: 7364170 (Open Web Text)

Max Activating Token Index: 287

Text #8

Max Range: 4.9494. Min Range: -4.9494

Max Act: 4.5556. Min Act: -0.1700

Data Index: 541199 (Open Web Text)

Max Activating Token Index: 922

Text #9

Max Range: 4.9494. Min Range: -4.9494

Max Act: 4.5025. Min Act: -0.1700

Data Index: 2992512 (Open Web Text)

Max Activating Token Index: 187

Text #10

Max Range: 4.9494. Min Range: -4.9494

Max Act: 4.4783. Min Act: -0.1700

Data Index: 168943 (Open Web Text)

Max Activating Token Index: 883

Text #11

Max Range: 4.9494. Min Range: -4.9494

Max Act: 4.4778. Min Act: -0.1700

Data Index: 7599173 (Open Web Text)

Max Activating Token Index: 91

Text #12

Max Range: 4.9494. Min Range: -4.9494

Max Act: 4.5008. Min Act: -0.1700

Data Index: 4604341 (Open Web Text)

Max Activating Token Index: 829

Text #13

Max Range: 4.9494. Min Range: -4.9494

Max Act: 4.5078. Min Act: -0.1700

Data Index: 318722 (Open Web Text)

Max Activating Token Index: 445

Text #14

Max Range: 4.9494. Min Range: -4.9494

Max Act: 4.4970. Min Act: -0.1700

Data Index: 4454349 (Open Web Text)

Max Activating Token Index: 958

Text #15

Max Range: 4.9494. Min Range: -4.9494

Max Act: 4.4751. Min Act: -0.1700

Data Index: 2992511 (Open Web Text)

Max Activating Token Index: 279

Text #16

Max Range: 4.9494. Min Range: -4.9494

Max Act: 4.4070. Min Act: -0.1700

Data Index: 3199811 (Open Web Text)

Max Activating Token Index: 693

Text #17

Max Range: 4.9494. Min Range: -4.9494

Max Act: 4.4338. Min Act: -0.1700

Data Index: 6402959 (Open Web Text)

Max Activating Token Index: 453

Text #18

Max Range: 4.9494. Min Range: -4.9494

Max Act: 4.4621. Min Act: -0.1700

Data Index: 5495133 (Open Web Text)

Max Activating Token Index: 847

Text #19

Max Range: 4.9494. Min Range: -4.9494

Max Act: 4.3925. Min Act: -0.1700

Data Index: 899870 (Open Web Text)

Max Activating Token Index: 136