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

Dataset: Open Web Text

Neuron 1704 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: 3.7685. Min Range: -3.7685

Max Act: 3.7685. Min Act: -0.1700

Data Index: 1176637 (Open Web Text)

Max Activating Token Index: 524

Text #1

Max Range: 3.7685. Min Range: -3.7685

Max Act: 3.7492. Min Act: -0.1700

Data Index: 6232412 (Open Web Text)

Max Activating Token Index: 690

Text #2

Max Range: 3.7685. Min Range: -3.7685

Max Act: 3.7626. Min Act: -0.1700

Data Index: 3985509 (Open Web Text)

Max Activating Token Index: 410

Text #3

Max Range: 3.7685. Min Range: -3.7685

Max Act: 3.7279. Min Act: -0.1700

Data Index: 4525443 (Open Web Text)

Max Activating Token Index: 332

Text #4

Max Range: 3.7685. Min Range: -3.7685

Max Act: 3.7487. Min Act: -0.1700

Data Index: 5275815 (Open Web Text)

Max Activating Token Index: 886

Text #5

Max Range: 3.7685. Min Range: -3.7685

Max Act: 3.7458. Min Act: -0.1700

Data Index: 7811389 (Open Web Text)

Max Activating Token Index: 57

Text #6

Max Range: 3.7685. Min Range: -3.7685

Max Act: 3.7492. Min Act: -0.1700

Data Index: 1357286 (Open Web Text)

Max Activating Token Index: 410

Text #7

Max Range: 3.7685. Min Range: -3.7685

Max Act: 3.7143. Min Act: -0.1700

Data Index: 5338411 (Open Web Text)

Max Activating Token Index: 539

Text #8

Max Range: 3.7685. Min Range: -3.7685

Max Act: 3.7305. Min Act: -0.1700

Data Index: 8439884 (Open Web Text)

Max Activating Token Index: 335

Text #9

Max Range: 3.7685. Min Range: -3.7685

Max Act: 3.7286. Min Act: -0.1700

Data Index: 1479338 (Open Web Text)

Max Activating Token Index: 993

Text #10

Max Range: 3.7685. Min Range: -3.7685

Max Act: 3.6955. Min Act: -0.1700

Data Index: 3448618 (Open Web Text)

Max Activating Token Index: 309

Text #11

Max Range: 3.7685. Min Range: -3.7685

Max Act: 3.7125. Min Act: -0.1700

Data Index: 7133084 (Open Web Text)

Max Activating Token Index: 192

Text #12

Max Range: 3.7685. Min Range: -3.7685

Max Act: 3.7402. Min Act: -0.1700

Data Index: 6691650 (Open Web Text)

Max Activating Token Index: 387

Text #13

Max Range: 3.7685. Min Range: -3.7685

Max Act: 3.6967. Min Act: -0.1700

Data Index: 6562628 (Open Web Text)

Max Activating Token Index: 424

Text #14

Max Range: 3.7685. Min Range: -3.7685

Max Act: 3.6696. Min Act: -0.1700

Data Index: 7254090 (Open Web Text)

Max Activating Token Index: 121

Text #15

Max Range: 3.7685. Min Range: -3.7685

Max Act: 3.6685. Min Act: -0.1700

Data Index: 4857490 (Open Web Text)

Max Activating Token Index: 819

Text #16

Max Range: 3.7685. Min Range: -3.7685

Max Act: 3.6990. Min Act: -0.1700

Data Index: 6303925 (Open Web Text)

Max Activating Token Index: 365

Text #17

Max Range: 3.7685. Min Range: -3.7685

Max Act: 3.6906. Min Act: -0.1700

Data Index: 8528 (Open Web Text)

Max Activating Token Index: 273

Text #18

Max Range: 3.7685. Min Range: -3.7685

Max Act: 3.6794. Min Act: -0.1700

Data Index: 7975212 (Open Web Text)

Max Activating Token Index: 725

Text #19

Max Range: 3.7685. Min Range: -3.7685

Max Act: 3.6592. Min Act: -0.1700

Data Index: 5465068 (Open Web Text)

Max Activating Token Index: 745