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

Dataset: Open Web Text

Neuron 2542 in Layer 5

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: 5.4485. Min Range: -5.4485

Max Act: 5.4485. Min Act: -0.1700

Data Index: 738019 (Open Web Text)

Max Activating Token Index: 228

Text #1

Max Range: 5.4485. Min Range: -5.4485

Max Act: 5.4094. Min Act: -0.1700

Data Index: 7831882 (Open Web Text)

Max Activating Token Index: 842

Text #2

Max Range: 5.4485. Min Range: -5.4485

Max Act: 5.3291. Min Act: -0.1700

Data Index: 1808858 (Open Web Text)

Max Activating Token Index: 333

Text #3

Max Range: 5.4485. Min Range: -5.4485

Max Act: 5.3197. Min Act: -0.1700

Data Index: 6536287 (Open Web Text)

Max Activating Token Index: 492

Text #4

Max Range: 5.4485. Min Range: -5.4485

Max Act: 5.3135. Min Act: -0.1700

Data Index: 6427662 (Open Web Text)

Max Activating Token Index: 624

Text #5

Max Range: 5.4485. Min Range: -5.4485

Max Act: 5.3193. Min Act: -0.1700

Data Index: 3682597 (Open Web Text)

Max Activating Token Index: 954

Text #6

Max Range: 5.4485. Min Range: -5.4485

Max Act: 5.3204. Min Act: -0.1700

Data Index: 6539663 (Open Web Text)

Max Activating Token Index: 313

Text #7

Max Range: 5.4485. Min Range: -5.4485

Max Act: 5.3008. Min Act: -0.1700

Data Index: 7069909 (Open Web Text)

Max Activating Token Index: 898

Text #8

Max Range: 5.4485. Min Range: -5.4485

Max Act: 5.2904. Min Act: -0.1700

Data Index: 5539545 (Open Web Text)

Max Activating Token Index: 224

Text #9

Max Range: 5.4485. Min Range: -5.4485

Max Act: 5.3070. Min Act: -0.1700

Data Index: 2859921 (Open Web Text)

Max Activating Token Index: 869

Text #10

Max Range: 5.4485. Min Range: -5.4485

Max Act: 5.3131. Min Act: -0.1700

Data Index: 7859826 (Open Web Text)

Max Activating Token Index: 138

Text #11

Max Range: 5.4485. Min Range: -5.4485

Max Act: 5.2456. Min Act: -0.1700

Data Index: 6133254 (Open Web Text)

Max Activating Token Index: 971

Text #12

Max Range: 5.4485. Min Range: -5.4485

Max Act: 5.2602. Min Act: -0.1700

Data Index: 6407948 (Open Web Text)

Max Activating Token Index: 717

Text #13

Max Range: 5.4485. Min Range: -5.4485

Max Act: 5.2482. Min Act: -0.1700

Data Index: 4805848 (Open Web Text)

Max Activating Token Index: 665

Text #14

Max Range: 5.4485. Min Range: -5.4485

Max Act: 5.2692. Min Act: -0.1700

Data Index: 4657649 (Open Web Text)

Max Activating Token Index: 264

Text #15

Max Range: 5.4485. Min Range: -5.4485

Max Act: 5.2544. Min Act: -0.1700

Data Index: 180272 (Open Web Text)

Max Activating Token Index: 237

Text #16

Max Range: 5.4485. Min Range: -5.4485

Max Act: 5.2027. Min Act: -0.1700

Data Index: 3306277 (Open Web Text)

Max Activating Token Index: 533

Text #17

Max Range: 5.4485. Min Range: -5.4485

Max Act: 5.2475. Min Act: -0.1700

Data Index: 5804077 (Open Web Text)

Max Activating Token Index: 669

Text #18

Max Range: 5.4485. Min Range: -5.4485

Max Act: 5.2395. Min Act: -0.1700

Data Index: 6142722 (Open Web Text)

Max Activating Token Index: 948

Text #19

Max Range: 5.4485. Min Range: -5.4485

Max Act: 5.2443. Min Act: -0.1700

Data Index: 4053589 (Open Web Text)

Max Activating Token Index: 288