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

Dataset: Open Web Text

Neuron 194 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: 4.0343. Min Range: -4.0343

Max Act: 4.0328. Min Act: -0.1700

Data Index: 6148121 (Open Web Text)

Max Activating Token Index: 763

Text #1

Max Range: 4.0343. Min Range: -4.0343

Max Act: 4.0168. Min Act: -0.1700

Data Index: 1171820 (Open Web Text)

Max Activating Token Index: 759

Text #2

Max Range: 4.0343. Min Range: -4.0343

Max Act: 4.0343. Min Act: -0.1700

Data Index: 3414754 (Open Web Text)

Max Activating Token Index: 466

Text #3

Max Range: 4.0343. Min Range: -4.0343

Max Act: 3.9796. Min Act: -0.1700

Data Index: 5165975 (Open Web Text)

Max Activating Token Index: 640

Text #4

Max Range: 4.0343. Min Range: -4.0343

Max Act: 3.9649. Min Act: -0.1700

Data Index: 7767798 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 4.0343. Min Range: -4.0343

Max Act: 3.9486. Min Act: -0.1700

Data Index: 8200139 (Open Web Text)

Max Activating Token Index: 113

Text #6

Max Range: 4.0343. Min Range: -4.0343

Max Act: 3.8734. Min Act: -0.1700

Data Index: 404438 (Open Web Text)

Max Activating Token Index: 361

Text #7

Max Range: 4.0343. Min Range: -4.0343

Max Act: 3.8528. Min Act: -0.1700

Data Index: 8082541 (Open Web Text)

Max Activating Token Index: 738

Text #8

Max Range: 4.0343. Min Range: -4.0343

Max Act: 3.8295. Min Act: -0.1700

Data Index: 1402723 (Open Web Text)

Max Activating Token Index: 944

Text #9

Max Range: 4.0343. Min Range: -4.0343

Max Act: 3.8517. Min Act: -0.1700

Data Index: 6181157 (Open Web Text)

Max Activating Token Index: 766

Text #10

Max Range: 4.0343. Min Range: -4.0343

Max Act: 3.8368. Min Act: -0.1700

Data Index: 8534229 (Open Web Text)

Max Activating Token Index: 641

Text #11

Max Range: 4.0343. Min Range: -4.0343

Max Act: 3.8259. Min Act: -0.1700

Data Index: 6952132 (Open Web Text)

Max Activating Token Index: 309

Text #12

Max Range: 4.0343. Min Range: -4.0343

Max Act: 3.8208. Min Act: -0.1700

Data Index: 4734153 (Open Web Text)

Max Activating Token Index: 197

Text #13

Max Range: 4.0343. Min Range: -4.0343

Max Act: 3.8282. Min Act: -0.1700

Data Index: 3805222 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 4.0343. Min Range: -4.0343

Max Act: 3.8240. Min Act: -0.1700

Data Index: 5834862 (Open Web Text)

Max Activating Token Index: 532

Text #15

Max Range: 4.0343. Min Range: -4.0343

Max Act: 3.7758. Min Act: -0.1700

Data Index: 3012124 (Open Web Text)

Max Activating Token Index: 946

Text #16

Max Range: 4.0343. Min Range: -4.0343

Max Act: 3.7831. Min Act: -0.1700

Data Index: 8023705 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 4.0343. Min Range: -4.0343

Max Act: 3.7128. Min Act: -0.1700

Data Index: 4516432 (Open Web Text)

Max Activating Token Index: 1007

Text #18

Max Range: 4.0343. Min Range: -4.0343

Max Act: 3.7653. Min Act: -0.1700

Data Index: 3781970 (Open Web Text)

Max Activating Token Index: 684

Text #19

Max Range: 4.0343. Min Range: -4.0343

Max Act: 3.7636. Min Act: -0.1700

Data Index: 2717085 (Open Web Text)

Max Activating Token Index: 431