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

Dataset: Open Web Text

Neuron 2976 in Layer 1

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: 3.4658. Min Range: -3.4658

Max Act: 3.4658. Min Act: -0.1700

Data Index: 2322335 (Open Web Text)

Max Activating Token Index: 48

Text #1

Max Range: 3.4658. Min Range: -3.4658

Max Act: 3.3907. Min Act: -0.1700

Data Index: 4513010 (Open Web Text)

Max Activating Token Index: 130

Text #2

Max Range: 3.4658. Min Range: -3.4658

Max Act: 3.3553. Min Act: -0.1700

Data Index: 4666899 (Open Web Text)

Max Activating Token Index: 32

Text #3

Max Range: 3.4658. Min Range: -3.4658

Max Act: 3.3477. Min Act: -0.1700

Data Index: 3057116 (Open Web Text)

Max Activating Token Index: 212

Text #4

Max Range: 3.4658. Min Range: -3.4658

Max Act: 3.3129. Min Act: -0.1700

Data Index: 7690184 (Open Web Text)

Max Activating Token Index: 45

Text #5

Max Range: 3.4658. Min Range: -3.4658

Max Act: 3.2932. Min Act: -0.1700

Data Index: 4164078 (Open Web Text)

Max Activating Token Index: 633

Text #6

Max Range: 3.4658. Min Range: -3.4658

Max Act: 3.3297. Min Act: -0.1700

Data Index: 7055776 (Open Web Text)

Max Activating Token Index: 557

Text #7

Max Range: 3.4658. Min Range: -3.4658

Max Act: 3.2733. Min Act: -0.1700

Data Index: 6085768 (Open Web Text)

Max Activating Token Index: 61

Text #8

Max Range: 3.4658. Min Range: -3.4658

Max Act: 3.2894. Min Act: -0.1700

Data Index: 6503538 (Open Web Text)

Max Activating Token Index: 626

Text #9

Max Range: 3.4658. Min Range: -3.4658

Max Act: 3.2777. Min Act: -0.1700

Data Index: 2789799 (Open Web Text)

Max Activating Token Index: 249

Text #10

Max Range: 3.4658. Min Range: -3.4658

Max Act: 3.2781. Min Act: -0.1700

Data Index: 1418435 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.4658. Min Range: -3.4658

Max Act: 3.2985. Min Act: -0.1700

Data Index: 2624482 (Open Web Text)

Max Activating Token Index: 431

Text #12

Max Range: 3.4658. Min Range: -3.4658

Max Act: 3.2819. Min Act: -0.1700

Data Index: 5683694 (Open Web Text)

Max Activating Token Index: 126

Text #13

Max Range: 3.4658. Min Range: -3.4658

Max Act: 3.3027. Min Act: -0.1700

Data Index: 5667809 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.4658. Min Range: -3.4658

Max Act: 3.2776. Min Act: -0.1700

Data Index: 2397078 (Open Web Text)

Max Activating Token Index: 14

Text #15

Max Range: 3.4658. Min Range: -3.4658

Max Act: 3.2559. Min Act: -0.1700

Data Index: 8643888 (Open Web Text)

Max Activating Token Index: 386

Text #16

Max Range: 3.4658. Min Range: -3.4658

Max Act: 3.2461. Min Act: -0.1700

Data Index: 3997230 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.4658. Min Range: -3.4658

Max Act: 3.2606. Min Act: -0.1700

Data Index: 3522431 (Open Web Text)

Max Activating Token Index: 156

Text #18

Max Range: 3.4658. Min Range: -3.4658

Max Act: 3.2933. Min Act: -0.1700

Data Index: 5101394 (Open Web Text)

Max Activating Token Index: 203

Text #19

Max Range: 3.4658. Min Range: -3.4658

Max Act: 3.2657. Min Act: -0.1700

Data Index: 8037880 (Open Web Text)

Max Activating Token Index: 542