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

Dataset: Open Web Text

Neuron 1540 in Layer 1

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: 2.2675. Min Range: -2.2675

Max Act: 2.2589. Min Act: -0.1700

Data Index: 3766459 (Open Web Text)

Max Activating Token Index: 462

Text #1

Max Range: 2.2675. Min Range: -2.2675

Max Act: 2.2567. Min Act: -0.1700

Data Index: 5589377 (Open Web Text)

Max Activating Token Index: 16

Text #2

Max Range: 2.2675. Min Range: -2.2675

Max Act: 2.2675. Min Act: -0.1700

Data Index: 2945907 (Open Web Text)

Max Activating Token Index: 401

Text #3

Max Range: 2.2675. Min Range: -2.2675

Max Act: 2.2583. Min Act: -0.1700

Data Index: 5930084 (Open Web Text)

Max Activating Token Index: 406

Text #4

Max Range: 2.2675. Min Range: -2.2675

Max Act: 2.2397. Min Act: -0.1700

Data Index: 5230630 (Open Web Text)

Max Activating Token Index: 596

Text #5

Max Range: 2.2675. Min Range: -2.2675

Max Act: 2.2525. Min Act: -0.1700

Data Index: 148350 (Open Web Text)

Max Activating Token Index: 417

Text #6

Max Range: 2.2675. Min Range: -2.2675

Max Act: 2.2594. Min Act: -0.1700

Data Index: 7099439 (Open Web Text)

Max Activating Token Index: 179

Text #7

Max Range: 2.2675. Min Range: -2.2675

Max Act: 2.2547. Min Act: -0.1700

Data Index: 3019409 (Open Web Text)

Max Activating Token Index: 18

Text #8

Max Range: 2.2675. Min Range: -2.2675

Max Act: 2.2496. Min Act: -0.1700

Data Index: 8733020 (Open Web Text)

Max Activating Token Index: 102

Text #9

Max Range: 2.2675. Min Range: -2.2675

Max Act: 2.2405. Min Act: -0.1700

Data Index: 8536894 (Open Web Text)

Max Activating Token Index: 15

Text #10

Max Range: 2.2675. Min Range: -2.2675

Max Act: 2.2397. Min Act: -0.1700

Data Index: 1935167 (Open Web Text)

Max Activating Token Index: 225

Text #11

Max Range: 2.2675. Min Range: -2.2675

Max Act: 2.2217. Min Act: -0.1700

Data Index: 6170662 (Open Web Text)

Max Activating Token Index: 368

Text #12

Max Range: 2.2675. Min Range: -2.2675

Max Act: 2.2302. Min Act: -0.1700

Data Index: 3121691 (Open Web Text)

Max Activating Token Index: 212

Text #13

Max Range: 2.2675. Min Range: -2.2675

Max Act: 2.2327. Min Act: -0.1700

Data Index: 3762348 (Open Web Text)

Max Activating Token Index: 471

Text #14

Max Range: 2.2675. Min Range: -2.2675

Max Act: 2.2377. Min Act: -0.1700

Data Index: 8416544 (Open Web Text)

Max Activating Token Index: 326

Text #15

Max Range: 2.2675. Min Range: -2.2675

Max Act: 2.2185. Min Act: -0.1700

Data Index: 5655774 (Open Web Text)

Max Activating Token Index: 685

Text #16

Max Range: 2.2675. Min Range: -2.2675

Max Act: 2.2428. Min Act: -0.1700

Data Index: 7928914 (Open Web Text)

Max Activating Token Index: 627

Text #17

Max Range: 2.2675. Min Range: -2.2675

Max Act: 2.2227. Min Act: -0.1700

Data Index: 7341377 (Open Web Text)

Max Activating Token Index: 113

Text #18

Max Range: 2.2675. Min Range: -2.2675

Max Act: 2.2261. Min Act: -0.1700

Data Index: 7518315 (Open Web Text)

Max Activating Token Index: 398

Text #19

Max Range: 2.2675. Min Range: -2.2675

Max Act: 2.2259. Min Act: -0.1700

Data Index: 5373913 (Open Web Text)

Max Activating Token Index: 450