Model: GELU Model: 1 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1006 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.4428. Min Range: -3.4428

Max Act: 3.4428. Min Act: -0.1700

Data Index: 467646 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 3.4428. Min Range: -3.4428

Max Act: 3.3575. Min Act: -0.1700

Data Index: 1025548 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 3.4428. Min Range: -3.4428

Max Act: 3.3205. Min Act: -0.1700

Data Index: 1346987 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 3.4428. Min Range: -3.4428

Max Act: 3.3014. Min Act: -0.1700

Data Index: 471362 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 3.4428. Min Range: -3.4428

Max Act: 3.2779. Min Act: -0.1700

Data Index: 1187931 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 3.4428. Min Range: -3.4428

Max Act: 3.2804. Min Act: -0.1700

Data Index: 529014 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 3.4428. Min Range: -3.4428

Max Act: 3.2666. Min Act: -0.1700

Data Index: 727681 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 3.4428. Min Range: -3.4428

Max Act: 3.2407. Min Act: -0.1700

Data Index: 828651 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 3.4428. Min Range: -3.4428

Max Act: 3.2412. Min Act: -0.1699

Data Index: 1143845 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 3.4428. Min Range: -3.4428

Max Act: 3.2279. Min Act: -0.1700

Data Index: 1226076 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 3.4428. Min Range: -3.4428

Max Act: 3.2325. Min Act: -0.1698

Data Index: 1278026 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 3.4428. Min Range: -3.4428

Max Act: 3.2294. Min Act: -0.1700

Data Index: 890714 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 3.4428. Min Range: -3.4428

Max Act: 3.2265. Min Act: -0.1699

Data Index: 1222341 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 3.4428. Min Range: -3.4428

Max Act: 3.2340. Min Act: -0.1700

Data Index: 726670 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 3.4428. Min Range: -3.4428

Max Act: 3.2179. Min Act: -0.1700

Data Index: 325908 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 3.4428. Min Range: -3.4428

Max Act: 3.2241. Min Act: -0.1700

Data Index: 257286 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 3.4428. Min Range: -3.4428

Max Act: 3.2212. Min Act: -0.1700

Data Index: 290379 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 3.4428. Min Range: -3.4428

Max Act: 3.1987. Min Act: -0.1700

Data Index: 398584 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 3.4428. Min Range: -3.4428

Max Act: 3.1893. Min Act: -0.1700

Data Index: 900728 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 3.4428. Min Range: -3.4428

Max Act: 3.1804. Min Act: -0.1700

Data Index: 92000 (C4 (Web Text))

Max Activating Token Index: 256