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

Dataset: Open Web Text

Neuron 1470 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: 1.9931. Min Range: -1.9931

Max Act: 1.9931. Min Act: -0.1700

Data Index: 6171246 (Open Web Text)

Max Activating Token Index: 51

Text #1

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.9678. Min Act: -0.1700

Data Index: 7398598 (Open Web Text)

Max Activating Token Index: 370

Text #2

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.9622. Min Act: -0.1700

Data Index: 8111344 (Open Web Text)

Max Activating Token Index: 456

Text #3

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.9560. Min Act: -0.1700

Data Index: 6934225 (Open Web Text)

Max Activating Token Index: 322

Text #4

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.9565. Min Act: -0.1700

Data Index: 6536065 (Open Web Text)

Max Activating Token Index: 556

Text #5

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.9518. Min Act: -0.1700

Data Index: 5129711 (Open Web Text)

Max Activating Token Index: 150

Text #6

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.9457. Min Act: -0.1700

Data Index: 2259950 (Open Web Text)

Max Activating Token Index: 264

Text #7

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.9456. Min Act: -0.1700

Data Index: 718662 (Open Web Text)

Max Activating Token Index: 35

Text #8

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.9462. Min Act: -0.1700

Data Index: 4312847 (Open Web Text)

Max Activating Token Index: 16

Text #9

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.9435. Min Act: -0.1700

Data Index: 8307507 (Open Web Text)

Max Activating Token Index: 575

Text #10

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.9460. Min Act: -0.1700

Data Index: 2508098 (Open Web Text)

Max Activating Token Index: 365

Text #11

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.9468. Min Act: -0.1700

Data Index: 3747329 (Open Web Text)

Max Activating Token Index: 43

Text #12

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.9617. Min Act: -0.1700

Data Index: 6621063 (Open Web Text)

Max Activating Token Index: 229

Text #13

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.9395. Min Act: -0.1700

Data Index: 4453405 (Open Web Text)

Max Activating Token Index: 135

Text #14

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.9351. Min Act: -0.1700

Data Index: 2640490 (Open Web Text)

Max Activating Token Index: 485

Text #15

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.9347. Min Act: -0.1700

Data Index: 4480746 (Open Web Text)

Max Activating Token Index: 531

Text #16

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.9325. Min Act: -0.1700

Data Index: 697164 (Open Web Text)

Max Activating Token Index: 687

Text #17

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.9323. Min Act: -0.1700

Data Index: 2519126 (Open Web Text)

Max Activating Token Index: 121

Text #18

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.9227. Min Act: -0.1700

Data Index: 2155751 (Open Web Text)

Max Activating Token Index: 619

Text #19

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.9376. Min Act: -0.1700

Data Index: 4628637 (Open Web Text)

Max Activating Token Index: 32