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

Dataset: Open Web Text

Neuron 1343 in Layer 5

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: 4.4146. Min Range: -4.4146

Max Act: 4.4146. Min Act: -0.1700

Data Index: 2106392 (Open Web Text)

Max Activating Token Index: 299

Text #1

Max Range: 4.4146. Min Range: -4.4146

Max Act: 4.3449. Min Act: -0.1700

Data Index: 3097627 (Open Web Text)

Max Activating Token Index: 216

Text #2

Max Range: 4.4146. Min Range: -4.4146

Max Act: 4.2771. Min Act: -0.1700

Data Index: 4877243 (Open Web Text)

Max Activating Token Index: 783

Text #3

Max Range: 4.4146. Min Range: -4.4146

Max Act: 4.2608. Min Act: -0.1700

Data Index: 3018917 (Open Web Text)

Max Activating Token Index: 189

Text #4

Max Range: 4.4146. Min Range: -4.4146

Max Act: 4.2946. Min Act: -0.1700

Data Index: 6371107 (Open Web Text)

Max Activating Token Index: 142

Text #5

Max Range: 4.4146. Min Range: -4.4146

Max Act: 4.2596. Min Act: -0.1700

Data Index: 368543 (Open Web Text)

Max Activating Token Index: 264

Text #6

Max Range: 4.4146. Min Range: -4.4146

Max Act: 4.2418. Min Act: -0.1700

Data Index: 1518905 (Open Web Text)

Max Activating Token Index: 538

Text #7

Max Range: 4.4146. Min Range: -4.4146

Max Act: 4.2235. Min Act: -0.1700

Data Index: 6704277 (Open Web Text)

Max Activating Token Index: 553

Text #8

Max Range: 4.4146. Min Range: -4.4146

Max Act: 4.2351. Min Act: -0.1700

Data Index: 1669392 (Open Web Text)

Max Activating Token Index: 149

Text #9

Max Range: 4.4146. Min Range: -4.4146

Max Act: 4.1417. Min Act: -0.1700

Data Index: 31863 (Open Web Text)

Max Activating Token Index: 308

Text #10

Max Range: 4.4146. Min Range: -4.4146

Max Act: 4.1406. Min Act: -0.1700

Data Index: 7178139 (Open Web Text)

Max Activating Token Index: 201

Text #11

Max Range: 4.4146. Min Range: -4.4146

Max Act: 4.1296. Min Act: -0.1700

Data Index: 4219652 (Open Web Text)

Max Activating Token Index: 717

Text #12

Max Range: 4.4146. Min Range: -4.4146

Max Act: 4.1517. Min Act: -0.1700

Data Index: 3984854 (Open Web Text)

Max Activating Token Index: 130

Text #13

Max Range: 4.4146. Min Range: -4.4146

Max Act: 4.1056. Min Act: -0.1700

Data Index: 1177967 (Open Web Text)

Max Activating Token Index: 751

Text #14

Max Range: 4.4146. Min Range: -4.4146

Max Act: 4.1601. Min Act: -0.1700

Data Index: 2617656 (Open Web Text)

Max Activating Token Index: 993

Text #15

Max Range: 4.4146. Min Range: -4.4146

Max Act: 4.1298. Min Act: -0.1700

Data Index: 4624468 (Open Web Text)

Max Activating Token Index: 446

Text #16

Max Range: 4.4146. Min Range: -4.4146

Max Act: 4.1274. Min Act: -0.1700

Data Index: 4610910 (Open Web Text)

Max Activating Token Index: 800

Text #17

Max Range: 4.4146. Min Range: -4.4146

Max Act: 4.1052. Min Act: -0.1700

Data Index: 2621834 (Open Web Text)

Max Activating Token Index: 45

Text #18

Max Range: 4.4146. Min Range: -4.4146

Max Act: 4.1155. Min Act: -0.1700

Data Index: 3711147 (Open Web Text)

Max Activating Token Index: 282

Text #19

Max Range: 4.4146. Min Range: -4.4146

Max Act: 4.1262. Min Act: -0.1700

Data Index: 2054243 (Open Web Text)

Max Activating Token Index: 957