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

Dataset: Open Web Text

Neuron 2646 in Layer 0

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: 1.0143. Min Range: -1.0143

Max Act: 1.0143. Min Act: -0.1670

Data Index: 2782584 (Open Web Text)

Max Activating Token Index: 815

Text #1

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.9887. Min Act: -0.1670

Data Index: 252089 (Open Web Text)

Max Activating Token Index: 469

Text #2

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.9825. Min Act: -0.1670

Data Index: 6294975 (Open Web Text)

Max Activating Token Index: 576

Text #3

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.9760. Min Act: -0.1670

Data Index: 2090953 (Open Web Text)

Max Activating Token Index: 373

Text #4

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.9722. Min Act: -0.1670

Data Index: 5276865 (Open Web Text)

Max Activating Token Index: 384

Text #5

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.9695. Min Act: -0.1671

Data Index: 5690986 (Open Web Text)

Max Activating Token Index: 387

Text #6

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.9624. Min Act: -0.1697

Data Index: 4750994 (Open Web Text)

Max Activating Token Index: 947

Text #7

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.9563. Min Act: -0.1670

Data Index: 6782586 (Open Web Text)

Max Activating Token Index: 312

Text #8

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.9531. Min Act: -0.1670

Data Index: 1521608 (Open Web Text)

Max Activating Token Index: 572

Text #9

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.9537. Min Act: -0.1696

Data Index: 3058206 (Open Web Text)

Max Activating Token Index: 995

Text #10

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.9544. Min Act: -0.1670

Data Index: 6294964 (Open Web Text)

Max Activating Token Index: 396

Text #11

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.9593. Min Act: -0.1670

Data Index: 3762158 (Open Web Text)

Max Activating Token Index: 604

Text #12

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.9436. Min Act: -0.1670

Data Index: 5427776 (Open Web Text)

Max Activating Token Index: 318

Text #13

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.9443. Min Act: -0.1670

Data Index: 4419206 (Open Web Text)

Max Activating Token Index: 231

Text #14

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.9498. Min Act: -0.1670

Data Index: 5903617 (Open Web Text)

Max Activating Token Index: 537

Text #15

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.9442. Min Act: -0.1670

Data Index: 2593375 (Open Web Text)

Max Activating Token Index: 1010

Text #16

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.9384. Min Act: -0.1670

Data Index: 4485285 (Open Web Text)

Max Activating Token Index: 42

Text #17

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.9440. Min Act: -0.1670

Data Index: 2765912 (Open Web Text)

Max Activating Token Index: 420

Text #18

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.9426. Min Act: -0.1670

Data Index: 652693 (Open Web Text)

Max Activating Token Index: 162

Text #19

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.9346. Min Act: -0.1670

Data Index: 4126888 (Open Web Text)

Max Activating Token Index: 287