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

Dataset: Open Web Text

Neuron 1704 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: 3.5497. Min Range: -3.5497

Max Act: 3.5497. Min Act: -0.1700

Data Index: 3493362 (Open Web Text)

Max Activating Token Index: 829

Text #1

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.5140. Min Act: -0.1700

Data Index: 1389445 (Open Web Text)

Max Activating Token Index: 369

Text #2

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.4799. Min Act: -0.1700

Data Index: 8538272 (Open Web Text)

Max Activating Token Index: 247

Text #3

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.4599. Min Act: -0.1700

Data Index: 7802854 (Open Web Text)

Max Activating Token Index: 241

Text #4

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.4376. Min Act: -0.1700

Data Index: 103889 (Open Web Text)

Max Activating Token Index: 607

Text #5

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.4505. Min Act: -0.1700

Data Index: 7048636 (Open Web Text)

Max Activating Token Index: 127

Text #6

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.4566. Min Act: -0.1700

Data Index: 4286800 (Open Web Text)

Max Activating Token Index: 237

Text #7

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.4320. Min Act: -0.1700

Data Index: 5144799 (Open Web Text)

Max Activating Token Index: 986

Text #8

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.4422. Min Act: -0.1700

Data Index: 8464857 (Open Web Text)

Max Activating Token Index: 371

Text #9

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.3986. Min Act: -0.1700

Data Index: 5471789 (Open Web Text)

Max Activating Token Index: 982

Text #10

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.3697. Min Act: -0.1700

Data Index: 3686510 (Open Web Text)

Max Activating Token Index: 108

Text #11

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.3805. Min Act: -0.1700

Data Index: 6078392 (Open Web Text)

Max Activating Token Index: 21

Text #12

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.3709. Min Act: -0.1700

Data Index: 4731582 (Open Web Text)

Max Activating Token Index: 645

Text #13

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.3567. Min Act: -0.1700

Data Index: 3691898 (Open Web Text)

Max Activating Token Index: 225

Text #14

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.3512. Min Act: -0.1700

Data Index: 2065001 (Open Web Text)

Max Activating Token Index: 387

Text #15

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.3262. Min Act: -0.1700

Data Index: 4536178 (Open Web Text)

Max Activating Token Index: 68

Text #16

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.3184. Min Act: -0.1700

Data Index: 6808855 (Open Web Text)

Max Activating Token Index: 194

Text #17

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.3158. Min Act: -0.1700

Data Index: 8147060 (Open Web Text)

Max Activating Token Index: 706

Text #18

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.3402. Min Act: -0.1700

Data Index: 1932288 (Open Web Text)

Max Activating Token Index: 61

Text #19

Max Range: 3.5497. Min Range: -3.5497

Max Act: 3.3243. Min Act: -0.1700

Data Index: 6269307 (Open Web Text)

Max Activating Token Index: 238