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

Dataset: Open Web Text

Neuron 891 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: 4.5541. Min Range: -4.5541

Max Act: 4.5541. Min Act: -0.1700

Data Index: 1066147 (Open Web Text)

Max Activating Token Index: 337

Text #1

Max Range: 4.5541. Min Range: -4.5541

Max Act: 4.4389. Min Act: -0.1700

Data Index: 5303743 (Open Web Text)

Max Activating Token Index: 921

Text #2

Max Range: 4.5541. Min Range: -4.5541

Max Act: 4.3702. Min Act: -0.1700

Data Index: 6898055 (Open Web Text)

Max Activating Token Index: 425

Text #3

Max Range: 4.5541. Min Range: -4.5541

Max Act: 4.4337. Min Act: -0.1700

Data Index: 8163802 (Open Web Text)

Max Activating Token Index: 799

Text #4

Max Range: 4.5541. Min Range: -4.5541

Max Act: 4.4192. Min Act: -0.1700

Data Index: 4742704 (Open Web Text)

Max Activating Token Index: 572

Text #5

Max Range: 4.5541. Min Range: -4.5541

Max Act: 4.3285. Min Act: -0.1700

Data Index: 68995 (Open Web Text)

Max Activating Token Index: 34

Text #6

Max Range: 4.5541. Min Range: -4.5541

Max Act: 4.3093. Min Act: -0.1700

Data Index: 58437 (Open Web Text)

Max Activating Token Index: 478

Text #7

Max Range: 4.5541. Min Range: -4.5541

Max Act: 4.3143. Min Act: -0.1700

Data Index: 7629479 (Open Web Text)

Max Activating Token Index: 207

Text #8

Max Range: 4.5541. Min Range: -4.5541

Max Act: 4.3146. Min Act: -0.1700

Data Index: 3500079 (Open Web Text)

Max Activating Token Index: 52

Text #9

Max Range: 4.5541. Min Range: -4.5541

Max Act: 4.2969. Min Act: -0.1700

Data Index: 5970863 (Open Web Text)

Max Activating Token Index: 491

Text #10

Max Range: 4.5541. Min Range: -4.5541

Max Act: 4.2757. Min Act: -0.1700

Data Index: 4190577 (Open Web Text)

Max Activating Token Index: 567

Text #11

Max Range: 4.5541. Min Range: -4.5541

Max Act: 4.2926. Min Act: -0.1700

Data Index: 7173738 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 4.5541. Min Range: -4.5541

Max Act: 4.2766. Min Act: -0.1700

Data Index: 113455 (Open Web Text)

Max Activating Token Index: 163

Text #13

Max Range: 4.5541. Min Range: -4.5541

Max Act: 4.3161. Min Act: -0.1700

Data Index: 4111002 (Open Web Text)

Max Activating Token Index: 956

Text #14

Max Range: 4.5541. Min Range: -4.5541

Max Act: 4.2450. Min Act: -0.1700

Data Index: 2890460 (Open Web Text)

Max Activating Token Index: 19

Text #15

Max Range: 4.5541. Min Range: -4.5541

Max Act: 4.2765. Min Act: -0.1700

Data Index: 5674430 (Open Web Text)

Max Activating Token Index: 483

Text #16

Max Range: 4.5541. Min Range: -4.5541

Max Act: 4.2713. Min Act: -0.1700

Data Index: 8183408 (Open Web Text)

Max Activating Token Index: 327

Text #17

Max Range: 4.5541. Min Range: -4.5541

Max Act: 4.2992. Min Act: -0.1700

Data Index: 1992086 (Open Web Text)

Max Activating Token Index: 902

Text #18

Max Range: 4.5541. Min Range: -4.5541

Max Act: 4.2613. Min Act: -0.1700

Data Index: 3198198 (Open Web Text)

Max Activating Token Index: 104

Text #19

Max Range: 4.5541. Min Range: -4.5541

Max Act: 4.2563. Min Act: -0.1700

Data Index: 6252356 (Open Web Text)

Max Activating Token Index: 34