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

Dataset: Open Web Text

Neuron 1191 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: 3.1806. Min Range: -3.1806

Max Act: 3.1806. Min Act: -0.1700

Data Index: 2740465 (Open Web Text)

Max Activating Token Index: 462

Text #1

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.1347. Min Act: -0.1700

Data Index: 8072384 (Open Web Text)

Max Activating Token Index: 410

Text #2

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0964. Min Act: -0.1700

Data Index: 2899984 (Open Web Text)

Max Activating Token Index: 451

Text #3

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0974. Min Act: -0.1700

Data Index: 5153360 (Open Web Text)

Max Activating Token Index: 915

Text #4

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0654. Min Act: -0.1700

Data Index: 3037593 (Open Web Text)

Max Activating Token Index: 366

Text #5

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0818. Min Act: -0.1700

Data Index: 3554114 (Open Web Text)

Max Activating Token Index: 51

Text #6

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0578. Min Act: -0.1700

Data Index: 2041151 (Open Web Text)

Max Activating Token Index: 708

Text #7

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0625. Min Act: -0.1700

Data Index: 1530370 (Open Web Text)

Max Activating Token Index: 855

Text #8

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0434. Min Act: -0.1700

Data Index: 3642534 (Open Web Text)

Max Activating Token Index: 739

Text #9

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0422. Min Act: -0.1700

Data Index: 5528021 (Open Web Text)

Max Activating Token Index: 978

Text #10

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0443. Min Act: -0.1700

Data Index: 6688512 (Open Web Text)

Max Activating Token Index: 905

Text #11

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0276. Min Act: -0.1700

Data Index: 2216119 (Open Web Text)

Max Activating Token Index: 600

Text #12

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0343. Min Act: -0.1700

Data Index: 8633166 (Open Web Text)

Max Activating Token Index: 985

Text #13

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0292. Min Act: -0.1700

Data Index: 216771 (Open Web Text)

Max Activating Token Index: 57

Text #14

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0354. Min Act: -0.1700

Data Index: 8278224 (Open Web Text)

Max Activating Token Index: 975

Text #15

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0407. Min Act: -0.1700

Data Index: 3862932 (Open Web Text)

Max Activating Token Index: 652

Text #16

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0309. Min Act: -0.1700

Data Index: 4183779 (Open Web Text)

Max Activating Token Index: 34

Text #17

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0443. Min Act: -0.1700

Data Index: 6246867 (Open Web Text)

Max Activating Token Index: 541

Text #18

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0188. Min Act: -0.1700

Data Index: 1999097 (Open Web Text)

Max Activating Token Index: 749

Text #19

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0082. Min Act: -0.1700

Data Index: 2003935 (Open Web Text)

Max Activating Token Index: 72