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

Dataset: Open Web Text

Neuron 109 in Layer 6

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: 4.7814. Min Range: -4.7814

Max Act: 4.7814. Min Act: -0.1700

Data Index: 7891244 (Open Web Text)

Max Activating Token Index: 634

Text #1

Max Range: 4.7814. Min Range: -4.7814

Max Act: 4.6613. Min Act: -0.1700

Data Index: 3610790 (Open Web Text)

Max Activating Token Index: 541

Text #2

Max Range: 4.7814. Min Range: -4.7814

Max Act: 4.6768. Min Act: -0.1700

Data Index: 7891247 (Open Web Text)

Max Activating Token Index: 194

Text #3

Max Range: 4.7814. Min Range: -4.7814

Max Act: 4.6515. Min Act: -0.1700

Data Index: 1444737 (Open Web Text)

Max Activating Token Index: 488

Text #4

Max Range: 4.7814. Min Range: -4.7814

Max Act: 4.5910. Min Act: -0.1700

Data Index: 1984902 (Open Web Text)

Max Activating Token Index: 526

Text #5

Max Range: 4.7814. Min Range: -4.7814

Max Act: 4.6204. Min Act: -0.1700

Data Index: 5054862 (Open Web Text)

Max Activating Token Index: 963

Text #6

Max Range: 4.7814. Min Range: -4.7814

Max Act: 4.6020. Min Act: -0.1700

Data Index: 432707 (Open Web Text)

Max Activating Token Index: 205

Text #7

Max Range: 4.7814. Min Range: -4.7814

Max Act: 4.5598. Min Act: -0.1700

Data Index: 8608985 (Open Web Text)

Max Activating Token Index: 260

Text #8

Max Range: 4.7814. Min Range: -4.7814

Max Act: 4.5655. Min Act: -0.1700

Data Index: 1396602 (Open Web Text)

Max Activating Token Index: 637

Text #9

Max Range: 4.7814. Min Range: -4.7814

Max Act: 4.5153. Min Act: -0.1700

Data Index: 8605756 (Open Web Text)

Max Activating Token Index: 489

Text #10

Max Range: 4.7814. Min Range: -4.7814

Max Act: 4.4939. Min Act: -0.1700

Data Index: 1396603 (Open Web Text)

Max Activating Token Index: 531

Text #11

Max Range: 4.7814. Min Range: -4.7814

Max Act: 4.4855. Min Act: -0.1700

Data Index: 8431258 (Open Web Text)

Max Activating Token Index: 513

Text #12

Max Range: 4.7814. Min Range: -4.7814

Max Act: 4.4466. Min Act: -0.1700

Data Index: 244254 (Open Web Text)

Max Activating Token Index: 566

Text #13

Max Range: 4.7814. Min Range: -4.7814

Max Act: 4.4423. Min Act: -0.1700

Data Index: 5610976 (Open Web Text)

Max Activating Token Index: 365

Text #14

Max Range: 4.7814. Min Range: -4.7814

Max Act: 4.4166. Min Act: -0.1700

Data Index: 2797211 (Open Web Text)

Max Activating Token Index: 590

Text #15

Max Range: 4.7814. Min Range: -4.7814

Max Act: 4.3945. Min Act: -0.1700

Data Index: 301509 (Open Web Text)

Max Activating Token Index: 484

Text #16

Max Range: 4.7814. Min Range: -4.7814

Max Act: 4.4282. Min Act: -0.1700

Data Index: 1633980 (Open Web Text)

Max Activating Token Index: 839

Text #17

Max Range: 4.7814. Min Range: -4.7814

Max Act: 4.4413. Min Act: -0.1700

Data Index: 301511 (Open Web Text)

Max Activating Token Index: 417

Text #18

Max Range: 4.7814. Min Range: -4.7814

Max Act: 4.4290. Min Act: -0.1700

Data Index: 3153491 (Open Web Text)

Max Activating Token Index: 739

Text #19

Max Range: 4.7814. Min Range: -4.7814

Max Act: 4.3917. Min Act: -0.1700

Data Index: 1887885 (Open Web Text)

Max Activating Token Index: 371