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

Dataset: Open Web Text

Neuron 843 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: 5.5942. Min Range: -5.5942

Max Act: 5.5942. Min Act: -0.1700

Data Index: 5435173 (Open Web Text)

Max Activating Token Index: 302

Text #1

Max Range: 5.5942. Min Range: -5.5942

Max Act: 5.5868. Min Act: -0.1700

Data Index: 2307153 (Open Web Text)

Max Activating Token Index: 332

Text #2

Max Range: 5.5942. Min Range: -5.5942

Max Act: 5.5677. Min Act: -0.1700

Data Index: 3070090 (Open Web Text)

Max Activating Token Index: 90

Text #3

Max Range: 5.5942. Min Range: -5.5942

Max Act: 5.5445. Min Act: -0.1700

Data Index: 1902596 (Open Web Text)

Max Activating Token Index: 532

Text #4

Max Range: 5.5942. Min Range: -5.5942

Max Act: 5.5349. Min Act: -0.1700

Data Index: 8462765 (Open Web Text)

Max Activating Token Index: 276

Text #5

Max Range: 5.5942. Min Range: -5.5942

Max Act: 5.4953. Min Act: -0.1700

Data Index: 6303981 (Open Web Text)

Max Activating Token Index: 778

Text #6

Max Range: 5.5942. Min Range: -5.5942

Max Act: 5.5154. Min Act: -0.1700

Data Index: 1243486 (Open Web Text)

Max Activating Token Index: 364

Text #7

Max Range: 5.5942. Min Range: -5.5942

Max Act: 5.4593. Min Act: -0.1700

Data Index: 6971904 (Open Web Text)

Max Activating Token Index: 414

Text #8

Max Range: 5.5942. Min Range: -5.5942

Max Act: 5.4661. Min Act: -0.1700

Data Index: 4831873 (Open Web Text)

Max Activating Token Index: 400

Text #9

Max Range: 5.5942. Min Range: -5.5942

Max Act: 5.4706. Min Act: -0.1700

Data Index: 195239 (Open Web Text)

Max Activating Token Index: 444

Text #10

Max Range: 5.5942. Min Range: -5.5942

Max Act: 5.4609. Min Act: -0.1700

Data Index: 716410 (Open Web Text)

Max Activating Token Index: 80

Text #11

Max Range: 5.5942. Min Range: -5.5942

Max Act: 5.4788. Min Act: -0.1700

Data Index: 7609030 (Open Web Text)

Max Activating Token Index: 550

Text #12

Max Range: 5.5942. Min Range: -5.5942

Max Act: 5.4736. Min Act: -0.1700

Data Index: 7406486 (Open Web Text)

Max Activating Token Index: 340

Text #13

Max Range: 5.5942. Min Range: -5.5942

Max Act: 5.4440. Min Act: -0.1700

Data Index: 2638404 (Open Web Text)

Max Activating Token Index: 359

Text #14

Max Range: 5.5942. Min Range: -5.5942

Max Act: 5.4393. Min Act: -0.1700

Data Index: 2617414 (Open Web Text)

Max Activating Token Index: 577

Text #15

Max Range: 5.5942. Min Range: -5.5942

Max Act: 5.4332. Min Act: -0.1700

Data Index: 1398764 (Open Web Text)

Max Activating Token Index: 37

Text #16

Max Range: 5.5942. Min Range: -5.5942

Max Act: 5.4448. Min Act: -0.1700

Data Index: 2085357 (Open Web Text)

Max Activating Token Index: 619

Text #17

Max Range: 5.5942. Min Range: -5.5942

Max Act: 5.4511. Min Act: -0.1700

Data Index: 4122882 (Open Web Text)

Max Activating Token Index: 606

Text #18

Max Range: 5.5942. Min Range: -5.5942

Max Act: 5.4282. Min Act: -0.1700

Data Index: 5286001 (Open Web Text)

Max Activating Token Index: 399

Text #19

Max Range: 5.5942. Min Range: -5.5942

Max Act: 5.4273. Min Act: -0.1700

Data Index: 5703690 (Open Web Text)

Max Activating Token Index: 166