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

Dataset: Open Web Text

Neuron 854 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: 1.3286. Min Range: -1.3286

Max Act: 1.3286. Min Act: -0.1699

Data Index: 8056274 (Open Web Text)

Max Activating Token Index: 958

Text #1

Max Range: 1.3286. Min Range: -1.3286

Max Act: 1.2947. Min Act: -0.1700

Data Index: 3368631 (Open Web Text)

Max Activating Token Index: 777

Text #2

Max Range: 1.3286. Min Range: -1.3286

Max Act: 1.3040. Min Act: -0.1700

Data Index: 7702031 (Open Web Text)

Max Activating Token Index: 109

Text #3

Max Range: 1.3286. Min Range: -1.3286

Max Act: 1.2878. Min Act: -0.1700

Data Index: 4932315 (Open Web Text)

Max Activating Token Index: 347

Text #4

Max Range: 1.3286. Min Range: -1.3286

Max Act: 1.2941. Min Act: -0.1700

Data Index: 8056277 (Open Web Text)

Max Activating Token Index: 399

Text #5

Max Range: 1.3286. Min Range: -1.3286

Max Act: 1.2692. Min Act: -0.1700

Data Index: 1647810 (Open Web Text)

Max Activating Token Index: 577

Text #6

Max Range: 1.3286. Min Range: -1.3286

Max Act: 1.2836. Min Act: -0.1699

Data Index: 483117 (Open Web Text)

Max Activating Token Index: 487

Text #7

Max Range: 1.3286. Min Range: -1.3286

Max Act: 1.2755. Min Act: -0.1700

Data Index: 5520978 (Open Web Text)

Max Activating Token Index: 638

Text #8

Max Range: 1.3286. Min Range: -1.3286

Max Act: 1.2659. Min Act: -0.1700

Data Index: 1647811 (Open Web Text)

Max Activating Token Index: 119

Text #9

Max Range: 1.3286. Min Range: -1.3286

Max Act: 1.2649. Min Act: -0.1700

Data Index: 8184964 (Open Web Text)

Max Activating Token Index: 100

Text #10

Max Range: 1.3286. Min Range: -1.3286

Max Act: 1.2559. Min Act: -0.1700

Data Index: 3540364 (Open Web Text)

Max Activating Token Index: 126

Text #11

Max Range: 1.3286. Min Range: -1.3286

Max Act: 1.2538. Min Act: -0.1700

Data Index: 7212717 (Open Web Text)

Max Activating Token Index: 221

Text #12

Max Range: 1.3286. Min Range: -1.3286

Max Act: 1.2516. Min Act: -0.1700

Data Index: 4677588 (Open Web Text)

Max Activating Token Index: 325

Text #13

Max Range: 1.3286. Min Range: -1.3286

Max Act: 1.2476. Min Act: -0.1700

Data Index: 6603837 (Open Web Text)

Max Activating Token Index: 484

Text #14

Max Range: 1.3286. Min Range: -1.3286

Max Act: 1.2573. Min Act: -0.1700

Data Index: 6531757 (Open Web Text)

Max Activating Token Index: 153

Text #15

Max Range: 1.3286. Min Range: -1.3286

Max Act: 1.2488. Min Act: -0.1700

Data Index: 3643729 (Open Web Text)

Max Activating Token Index: 55

Text #16

Max Range: 1.3286. Min Range: -1.3286

Max Act: 1.2649. Min Act: -0.1700

Data Index: 483118 (Open Web Text)

Max Activating Token Index: 429

Text #17

Max Range: 1.3286. Min Range: -1.3286

Max Act: 1.2595. Min Act: -0.1695

Data Index: 6362757 (Open Web Text)

Max Activating Token Index: 226

Text #18

Max Range: 1.3286. Min Range: -1.3286

Max Act: 1.2331. Min Act: -0.1700

Data Index: 1005498 (Open Web Text)

Max Activating Token Index: 407

Text #19

Max Range: 1.3286. Min Range: -1.3286

Max Act: 1.2377. Min Act: -0.1700

Data Index: 4865785 (Open Web Text)

Max Activating Token Index: 381