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

Dataset: Open Web Text

Neuron 2527 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: 4.2762. Min Range: -4.2762

Max Act: 4.2762. Min Act: -0.1700

Data Index: 7697048 (Open Web Text)

Max Activating Token Index: 570

Text #1

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1594. Min Act: -0.1700

Data Index: 5478901 (Open Web Text)

Max Activating Token Index: 469

Text #2

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1666. Min Act: -0.1700

Data Index: 534109 (Open Web Text)

Max Activating Token Index: 117

Text #3

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1271. Min Act: -0.1700

Data Index: 1149402 (Open Web Text)

Max Activating Token Index: 526

Text #4

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1341. Min Act: -0.1700

Data Index: 3193805 (Open Web Text)

Max Activating Token Index: 516

Text #5

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1334. Min Act: -0.1700

Data Index: 124299 (Open Web Text)

Max Activating Token Index: 69

Text #6

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1131. Min Act: -0.1700

Data Index: 3578826 (Open Web Text)

Max Activating Token Index: 403

Text #7

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1409. Min Act: -0.1700

Data Index: 5389907 (Open Web Text)

Max Activating Token Index: 261

Text #8

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1232. Min Act: -0.1700

Data Index: 7333082 (Open Web Text)

Max Activating Token Index: 684

Text #9

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1230. Min Act: -0.1700

Data Index: 2753742 (Open Web Text)

Max Activating Token Index: 84

Text #10

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1066. Min Act: -0.1700

Data Index: 7228827 (Open Web Text)

Max Activating Token Index: 570

Text #11

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1060. Min Act: -0.1700

Data Index: 216198 (Open Web Text)

Max Activating Token Index: 68

Text #12

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.0709. Min Act: -0.1700

Data Index: 6549077 (Open Web Text)

Max Activating Token Index: 131

Text #13

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.0796. Min Act: -0.1700

Data Index: 5716540 (Open Web Text)

Max Activating Token Index: 464

Text #14

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.0876. Min Act: -0.1700

Data Index: 5080560 (Open Web Text)

Max Activating Token Index: 244

Text #15

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.0533. Min Act: -0.1700

Data Index: 573428 (Open Web Text)

Max Activating Token Index: 438

Text #16

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.0854. Min Act: -0.1700

Data Index: 4541649 (Open Web Text)

Max Activating Token Index: 1007

Text #17

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.0827. Min Act: -0.1700

Data Index: 2292918 (Open Web Text)

Max Activating Token Index: 707

Text #18

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.0963. Min Act: -0.1700

Data Index: 3455671 (Open Web Text)

Max Activating Token Index: 89

Text #19

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.0569. Min Act: -0.1700

Data Index: 24484 (Open Web Text)

Max Activating Token Index: 87