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

Dataset: Open Web Text

Neuron 2947 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: 3.6652. Min Range: -3.6652

Max Act: 3.6652. Min Act: -0.1700

Data Index: 5486316 (Open Web Text)

Max Activating Token Index: 487

Text #1

Max Range: 3.6652. Min Range: -3.6652

Max Act: 3.5936. Min Act: -0.1700

Data Index: 2576970 (Open Web Text)

Max Activating Token Index: 175

Text #2

Max Range: 3.6652. Min Range: -3.6652

Max Act: 3.5438. Min Act: -0.1700

Data Index: 8512915 (Open Web Text)

Max Activating Token Index: 933

Text #3

Max Range: 3.6652. Min Range: -3.6652

Max Act: 3.4176. Min Act: -0.1700

Data Index: 8112182 (Open Web Text)

Max Activating Token Index: 55

Text #4

Max Range: 3.6652. Min Range: -3.6652

Max Act: 3.3607. Min Act: -0.1700

Data Index: 3302235 (Open Web Text)

Max Activating Token Index: 93

Text #5

Max Range: 3.6652. Min Range: -3.6652

Max Act: 3.2919. Min Act: -0.1700

Data Index: 706737 (Open Web Text)

Max Activating Token Index: 773

Text #6

Max Range: 3.6652. Min Range: -3.6652

Max Act: 3.2906. Min Act: -0.1700

Data Index: 2583775 (Open Web Text)

Max Activating Token Index: 225

Text #7

Max Range: 3.6652. Min Range: -3.6652

Max Act: 3.3143. Min Act: -0.1700

Data Index: 3913636 (Open Web Text)

Max Activating Token Index: 681

Text #8

Max Range: 3.6652. Min Range: -3.6652

Max Act: 3.2964. Min Act: -0.1700

Data Index: 3207247 (Open Web Text)

Max Activating Token Index: 705

Text #9

Max Range: 3.6652. Min Range: -3.6652

Max Act: 3.2968. Min Act: -0.1700

Data Index: 2097823 (Open Web Text)

Max Activating Token Index: 732

Text #10

Max Range: 3.6652. Min Range: -3.6652

Max Act: 3.2819. Min Act: -0.1700

Data Index: 7992247 (Open Web Text)

Max Activating Token Index: 988

Text #11

Max Range: 3.6652. Min Range: -3.6652

Max Act: 3.2601. Min Act: -0.1700

Data Index: 809475 (Open Web Text)

Max Activating Token Index: 267

Text #12

Max Range: 3.6652. Min Range: -3.6652

Max Act: 3.2559. Min Act: -0.1700

Data Index: 7083753 (Open Web Text)

Max Activating Token Index: 489

Text #13

Max Range: 3.6652. Min Range: -3.6652

Max Act: 3.2497. Min Act: -0.1700

Data Index: 5776643 (Open Web Text)

Max Activating Token Index: 645

Text #14

Max Range: 3.6652. Min Range: -3.6652

Max Act: 3.2466. Min Act: -0.1700

Data Index: 6529373 (Open Web Text)

Max Activating Token Index: 389

Text #15

Max Range: 3.6652. Min Range: -3.6652

Max Act: 3.2268. Min Act: -0.1700

Data Index: 7051893 (Open Web Text)

Max Activating Token Index: 64

Text #16

Max Range: 3.6652. Min Range: -3.6652

Max Act: 3.2251. Min Act: -0.1700

Data Index: 3518427 (Open Web Text)

Max Activating Token Index: 81

Text #17

Max Range: 3.6652. Min Range: -3.6652

Max Act: 3.2344. Min Act: -0.1700

Data Index: 3804590 (Open Web Text)

Max Activating Token Index: 321

Text #18

Max Range: 3.6652. Min Range: -3.6652

Max Act: 3.2218. Min Act: -0.1700

Data Index: 7026531 (Open Web Text)

Max Activating Token Index: 738

Text #19

Max Range: 3.6652. Min Range: -3.6652

Max Act: 3.2126. Min Act: -0.1700

Data Index: 7821156 (Open Web Text)

Max Activating Token Index: 190