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

Dataset: Open Web Text

Neuron 454 in Layer 2

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: 3.0557. Min Range: -3.0557

Max Act: 3.0557. Min Act: -0.1700

Data Index: 6258225 (Open Web Text)

Max Activating Token Index: 329

Text #1

Max Range: 3.0557. Min Range: -3.0557

Max Act: 3.0542. Min Act: -0.1700

Data Index: 8156523 (Open Web Text)

Max Activating Token Index: 462

Text #2

Max Range: 3.0557. Min Range: -3.0557

Max Act: 3.0277. Min Act: -0.1700

Data Index: 5885176 (Open Web Text)

Max Activating Token Index: 397

Text #3

Max Range: 3.0557. Min Range: -3.0557

Max Act: 3.0327. Min Act: -0.1700

Data Index: 7876648 (Open Web Text)

Max Activating Token Index: 386

Text #4

Max Range: 3.0557. Min Range: -3.0557

Max Act: 3.0390. Min Act: -0.1700

Data Index: 8515634 (Open Web Text)

Max Activating Token Index: 468

Text #5

Max Range: 3.0557. Min Range: -3.0557

Max Act: 3.0053. Min Act: -0.1700

Data Index: 1275372 (Open Web Text)

Max Activating Token Index: 684

Text #6

Max Range: 3.0557. Min Range: -3.0557

Max Act: 2.9691. Min Act: -0.1700

Data Index: 5416963 (Open Web Text)

Max Activating Token Index: 454

Text #7

Max Range: 3.0557. Min Range: -3.0557

Max Act: 2.9937. Min Act: -0.1700

Data Index: 2866585 (Open Web Text)

Max Activating Token Index: 673

Text #8

Max Range: 3.0557. Min Range: -3.0557

Max Act: 2.9958. Min Act: -0.1700

Data Index: 6882753 (Open Web Text)

Max Activating Token Index: 370

Text #9

Max Range: 3.0557. Min Range: -3.0557

Max Act: 2.9613. Min Act: -0.1700

Data Index: 4106763 (Open Web Text)

Max Activating Token Index: 401

Text #10

Max Range: 3.0557. Min Range: -3.0557

Max Act: 2.9758. Min Act: -0.1700

Data Index: 7082090 (Open Web Text)

Max Activating Token Index: 754

Text #11

Max Range: 3.0557. Min Range: -3.0557

Max Act: 2.9408. Min Act: -0.1700

Data Index: 7261404 (Open Web Text)

Max Activating Token Index: 572

Text #12

Max Range: 3.0557. Min Range: -3.0557

Max Act: 2.9438. Min Act: -0.1700

Data Index: 8191890 (Open Web Text)

Max Activating Token Index: 352

Text #13

Max Range: 3.0557. Min Range: -3.0557

Max Act: 2.9605. Min Act: -0.1700

Data Index: 1326025 (Open Web Text)

Max Activating Token Index: 390

Text #14

Max Range: 3.0557. Min Range: -3.0557

Max Act: 2.9341. Min Act: -0.1700

Data Index: 1561226 (Open Web Text)

Max Activating Token Index: 706

Text #15

Max Range: 3.0557. Min Range: -3.0557

Max Act: 2.9389. Min Act: -0.1700

Data Index: 322240 (Open Web Text)

Max Activating Token Index: 243

Text #16

Max Range: 3.0557. Min Range: -3.0557

Max Act: 2.9384. Min Act: -0.1700

Data Index: 3994148 (Open Web Text)

Max Activating Token Index: 624

Text #17

Max Range: 3.0557. Min Range: -3.0557

Max Act: 2.9138. Min Act: -0.1700

Data Index: 8385999 (Open Web Text)

Max Activating Token Index: 541

Text #18

Max Range: 3.0557. Min Range: -3.0557

Max Act: 2.9144. Min Act: -0.1700

Data Index: 5752922 (Open Web Text)

Max Activating Token Index: 526

Text #19

Max Range: 3.0557. Min Range: -3.0557

Max Act: 2.8969. Min Act: -0.1700

Data Index: 3994144 (Open Web Text)

Max Activating Token Index: 133