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

Dataset: Open Web Text

Neuron 2516 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: 3.4908. Min Range: -3.4908

Max Act: 3.4908. Min Act: -0.1700

Data Index: 8446649 (Open Web Text)

Max Activating Token Index: 978

Text #1

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.3399. Min Act: -0.1700

Data Index: 8222253 (Open Web Text)

Max Activating Token Index: 411

Text #2

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.3312. Min Act: -0.1700

Data Index: 3076426 (Open Web Text)

Max Activating Token Index: 732

Text #3

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.2703. Min Act: -0.1700

Data Index: 7565809 (Open Web Text)

Max Activating Token Index: 701

Text #4

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.2740. Min Act: -0.1700

Data Index: 5533256 (Open Web Text)

Max Activating Token Index: 148

Text #5

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.2324. Min Act: -0.1700

Data Index: 7253927 (Open Web Text)

Max Activating Token Index: 317

Text #6

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.2444. Min Act: -0.1700

Data Index: 2897489 (Open Web Text)

Max Activating Token Index: 232

Text #7

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.2354. Min Act: -0.1700

Data Index: 1098429 (Open Web Text)

Max Activating Token Index: 786

Text #8

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.2025. Min Act: -0.1700

Data Index: 4149442 (Open Web Text)

Max Activating Token Index: 956

Text #9

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.2241. Min Act: -0.1700

Data Index: 3085205 (Open Web Text)

Max Activating Token Index: 147

Text #10

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.2157. Min Act: -0.1700

Data Index: 8446646 (Open Web Text)

Max Activating Token Index: 438

Text #11

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.2039. Min Act: -0.1700

Data Index: 6090368 (Open Web Text)

Max Activating Token Index: 1014

Text #12

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.2032. Min Act: -0.1700

Data Index: 230718 (Open Web Text)

Max Activating Token Index: 760

Text #13

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.1595. Min Act: -0.1700

Data Index: 6032252 (Open Web Text)

Max Activating Token Index: 765

Text #14

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.1691. Min Act: -0.1700

Data Index: 2572807 (Open Web Text)

Max Activating Token Index: 139

Text #15

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.1707. Min Act: -0.1700

Data Index: 3652750 (Open Web Text)

Max Activating Token Index: 634

Text #16

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.1635. Min Act: -0.1700

Data Index: 4776026 (Open Web Text)

Max Activating Token Index: 928

Text #17

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.1456. Min Act: -0.1700

Data Index: 7754430 (Open Web Text)

Max Activating Token Index: 575

Text #18

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.1462. Min Act: -0.1700

Data Index: 3088428 (Open Web Text)

Max Activating Token Index: 133

Text #19

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.1386. Min Act: -0.1700

Data Index: 6833636 (Open Web Text)

Max Activating Token Index: 766