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

Dataset: Open Web Text

Neuron 1722 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: 3.4242. Min Range: -3.4242

Max Act: 3.4242. Min Act: -0.1700

Data Index: 7836187 (Open Web Text)

Max Activating Token Index: 144

Text #1

Max Range: 3.4242. Min Range: -3.4242

Max Act: 3.1646. Min Act: -0.1700

Data Index: 5813204 (Open Web Text)

Max Activating Token Index: 99

Text #2

Max Range: 3.4242. Min Range: -3.4242

Max Act: 3.1477. Min Act: -0.1700

Data Index: 805911 (Open Web Text)

Max Activating Token Index: 291

Text #3

Max Range: 3.4242. Min Range: -3.4242

Max Act: 3.1439. Min Act: -0.1700

Data Index: 3776063 (Open Web Text)

Max Activating Token Index: 560

Text #4

Max Range: 3.4242. Min Range: -3.4242

Max Act: 3.1283. Min Act: -0.1700

Data Index: 4357613 (Open Web Text)

Max Activating Token Index: 1017

Text #5

Max Range: 3.4242. Min Range: -3.4242

Max Act: 3.0900. Min Act: -0.1700

Data Index: 4472384 (Open Web Text)

Max Activating Token Index: 389

Text #6

Max Range: 3.4242. Min Range: -3.4242

Max Act: 3.0749. Min Act: -0.1700

Data Index: 5834916 (Open Web Text)

Max Activating Token Index: 966

Text #7

Max Range: 3.4242. Min Range: -3.4242

Max Act: 3.0771. Min Act: -0.1700

Data Index: 4525420 (Open Web Text)

Max Activating Token Index: 772

Text #8

Max Range: 3.4242. Min Range: -3.4242

Max Act: 3.0775. Min Act: -0.1700

Data Index: 2424214 (Open Web Text)

Max Activating Token Index: 846

Text #9

Max Range: 3.4242. Min Range: -3.4242

Max Act: 3.0446. Min Act: -0.1700

Data Index: 4321282 (Open Web Text)

Max Activating Token Index: 669

Text #10

Max Range: 3.4242. Min Range: -3.4242

Max Act: 3.0472. Min Act: -0.1700

Data Index: 8626421 (Open Web Text)

Max Activating Token Index: 641

Text #11

Max Range: 3.4242. Min Range: -3.4242

Max Act: 3.0400. Min Act: -0.1700

Data Index: 8059309 (Open Web Text)

Max Activating Token Index: 939

Text #12

Max Range: 3.4242. Min Range: -3.4242

Max Act: 3.0280. Min Act: -0.1700

Data Index: 8037607 (Open Web Text)

Max Activating Token Index: 540

Text #13

Max Range: 3.4242. Min Range: -3.4242

Max Act: 3.0524. Min Act: -0.1700

Data Index: 2250144 (Open Web Text)

Max Activating Token Index: 975

Text #14

Max Range: 3.4242. Min Range: -3.4242

Max Act: 3.0241. Min Act: -0.1700

Data Index: 4196462 (Open Web Text)

Max Activating Token Index: 888

Text #15

Max Range: 3.4242. Min Range: -3.4242

Max Act: 3.0140. Min Act: -0.1700

Data Index: 8782850 (Open Web Text)

Max Activating Token Index: 555

Text #16

Max Range: 3.4242. Min Range: -3.4242

Max Act: 3.0101. Min Act: -0.1700

Data Index: 4676696 (Open Web Text)

Max Activating Token Index: 387

Text #17

Max Range: 3.4242. Min Range: -3.4242

Max Act: 3.0207. Min Act: -0.1700

Data Index: 2782990 (Open Web Text)

Max Activating Token Index: 287

Text #18

Max Range: 3.4242. Min Range: -3.4242

Max Act: 3.0157. Min Act: -0.1700

Data Index: 4667007 (Open Web Text)

Max Activating Token Index: 553

Text #19

Max Range: 3.4242. Min Range: -3.4242

Max Act: 2.9927. Min Act: -0.1700

Data Index: 1658289 (Open Web Text)

Max Activating Token Index: 611