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

Dataset: Open Web Text

Neuron 1491 in Layer 4

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: 4.3547. Min Range: -4.3547

Max Act: 4.3547. Min Act: -0.1700

Data Index: 5157592 (Open Web Text)

Max Activating Token Index: 125

Text #1

Max Range: 4.3547. Min Range: -4.3547

Max Act: 4.3502. Min Act: -0.1700

Data Index: 2647183 (Open Web Text)

Max Activating Token Index: 977

Text #2

Max Range: 4.3547. Min Range: -4.3547

Max Act: 4.3418. Min Act: -0.1700

Data Index: 1760784 (Open Web Text)

Max Activating Token Index: 558

Text #3

Max Range: 4.3547. Min Range: -4.3547

Max Act: 4.3273. Min Act: -0.1700

Data Index: 4713943 (Open Web Text)

Max Activating Token Index: 286

Text #4

Max Range: 4.3547. Min Range: -4.3547

Max Act: 4.3370. Min Act: -0.1700

Data Index: 8526898 (Open Web Text)

Max Activating Token Index: 715

Text #5

Max Range: 4.3547. Min Range: -4.3547

Max Act: 4.2863. Min Act: -0.1700

Data Index: 4199959 (Open Web Text)

Max Activating Token Index: 878

Text #6

Max Range: 4.3547. Min Range: -4.3547

Max Act: 4.2900. Min Act: -0.1700

Data Index: 8520653 (Open Web Text)

Max Activating Token Index: 420

Text #7

Max Range: 4.3547. Min Range: -4.3547

Max Act: 4.2836. Min Act: -0.1700

Data Index: 1111218 (Open Web Text)

Max Activating Token Index: 329

Text #8

Max Range: 4.3547. Min Range: -4.3547

Max Act: 4.3034. Min Act: -0.1700

Data Index: 768860 (Open Web Text)

Max Activating Token Index: 510

Text #9

Max Range: 4.3547. Min Range: -4.3547

Max Act: 4.2856. Min Act: -0.1700

Data Index: 6833963 (Open Web Text)

Max Activating Token Index: 695

Text #10

Max Range: 4.3547. Min Range: -4.3547

Max Act: 4.2681. Min Act: -0.1700

Data Index: 380866 (Open Web Text)

Max Activating Token Index: 375

Text #11

Max Range: 4.3547. Min Range: -4.3547

Max Act: 4.2766. Min Act: -0.1700

Data Index: 539046 (Open Web Text)

Max Activating Token Index: 944

Text #12

Max Range: 4.3547. Min Range: -4.3547

Max Act: 4.2689. Min Act: -0.1700

Data Index: 729033 (Open Web Text)

Max Activating Token Index: 398

Text #13

Max Range: 4.3547. Min Range: -4.3547

Max Act: 4.2502. Min Act: -0.1700

Data Index: 888238 (Open Web Text)

Max Activating Token Index: 33

Text #14

Max Range: 4.3547. Min Range: -4.3547

Max Act: 4.2412. Min Act: -0.1700

Data Index: 3094862 (Open Web Text)

Max Activating Token Index: 331

Text #15

Max Range: 4.3547. Min Range: -4.3547

Max Act: 4.2425. Min Act: -0.1700

Data Index: 81420 (Open Web Text)

Max Activating Token Index: 251

Text #16

Max Range: 4.3547. Min Range: -4.3547

Max Act: 4.2401. Min Act: -0.1700

Data Index: 7388805 (Open Web Text)

Max Activating Token Index: 390

Text #17

Max Range: 4.3547. Min Range: -4.3547

Max Act: 4.2234. Min Act: -0.1700

Data Index: 7495021 (Open Web Text)

Max Activating Token Index: 550

Text #18

Max Range: 4.3547. Min Range: -4.3547

Max Act: 4.2280. Min Act: -0.1700

Data Index: 4710747 (Open Web Text)

Max Activating Token Index: 66

Text #19

Max Range: 4.3547. Min Range: -4.3547

Max Act: 4.2282. Min Act: -0.1700

Data Index: 8012291 (Open Web Text)

Max Activating Token Index: 305