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

Dataset: Open Web Text

Neuron 1008 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: 4.9700. Min Range: -4.9700

Max Act: 4.9700. Min Act: -0.1700

Data Index: 1961188 (Open Web Text)

Max Activating Token Index: 602

Text #1

Max Range: 4.9700. Min Range: -4.9700

Max Act: 4.8478. Min Act: -0.1700

Data Index: 6826936 (Open Web Text)

Max Activating Token Index: 801

Text #2

Max Range: 4.9700. Min Range: -4.9700

Max Act: 4.7827. Min Act: -0.1700

Data Index: 2572094 (Open Web Text)

Max Activating Token Index: 524

Text #3

Max Range: 4.9700. Min Range: -4.9700

Max Act: 4.7988. Min Act: -0.1700

Data Index: 2103287 (Open Web Text)

Max Activating Token Index: 587

Text #4

Max Range: 4.9700. Min Range: -4.9700

Max Act: 4.7237. Min Act: -0.1700

Data Index: 1558268 (Open Web Text)

Max Activating Token Index: 829

Text #5

Max Range: 4.9700. Min Range: -4.9700

Max Act: 4.7212. Min Act: -0.1700

Data Index: 3689776 (Open Web Text)

Max Activating Token Index: 714

Text #6

Max Range: 4.9700. Min Range: -4.9700

Max Act: 4.7711. Min Act: -0.1700

Data Index: 1211424 (Open Web Text)

Max Activating Token Index: 772

Text #7

Max Range: 4.9700. Min Range: -4.9700

Max Act: 4.7340. Min Act: -0.1700

Data Index: 3074332 (Open Web Text)

Max Activating Token Index: 220

Text #8

Max Range: 4.9700. Min Range: -4.9700

Max Act: 4.7089. Min Act: -0.1700

Data Index: 355944 (Open Web Text)

Max Activating Token Index: 288

Text #9

Max Range: 4.9700. Min Range: -4.9700

Max Act: 4.6550. Min Act: -0.1700

Data Index: 500626 (Open Web Text)

Max Activating Token Index: 333

Text #10

Max Range: 4.9700. Min Range: -4.9700

Max Act: 4.7634. Min Act: -0.1700

Data Index: 1061594 (Open Web Text)

Max Activating Token Index: 1009

Text #11

Max Range: 4.9700. Min Range: -4.9700

Max Act: 4.7102. Min Act: -0.1700

Data Index: 3347894 (Open Web Text)

Max Activating Token Index: 301

Text #12

Max Range: 4.9700. Min Range: -4.9700

Max Act: 4.6727. Min Act: -0.1700

Data Index: 7298827 (Open Web Text)

Max Activating Token Index: 555

Text #13

Max Range: 4.9700. Min Range: -4.9700

Max Act: 4.6437. Min Act: -0.1700

Data Index: 913571 (Open Web Text)

Max Activating Token Index: 399

Text #14

Max Range: 4.9700. Min Range: -4.9700

Max Act: 4.6702. Min Act: -0.1700

Data Index: 6455438 (Open Web Text)

Max Activating Token Index: 176

Text #15

Max Range: 4.9700. Min Range: -4.9700

Max Act: 4.5259. Min Act: -0.1700

Data Index: 7122739 (Open Web Text)

Max Activating Token Index: 415

Text #16

Max Range: 4.9700. Min Range: -4.9700

Max Act: 4.6307. Min Act: -0.1700

Data Index: 2560395 (Open Web Text)

Max Activating Token Index: 990

Text #17

Max Range: 4.9700. Min Range: -4.9700

Max Act: 4.5161. Min Act: -0.1700

Data Index: 7424292 (Open Web Text)

Max Activating Token Index: 362

Text #18

Max Range: 4.9700. Min Range: -4.9700

Max Act: 4.5921. Min Act: -0.1700

Data Index: 2996080 (Open Web Text)

Max Activating Token Index: 530

Text #19

Max Range: 4.9700. Min Range: -4.9700

Max Act: 4.5591. Min Act: -0.1700

Data Index: 6577613 (Open Web Text)

Max Activating Token Index: 498