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

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

Neuron 583 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: 3.6372. Min Range: -3.6372

Max Act: 3.6372. Min Act: -0.1693

Data Index: 1303898 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.5740. Min Act: -0.1667

Data Index: 293019 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.5670. Min Act: -0.1696

Data Index: 571131 (C4 (Web Text))

Max Activating Token Index: 535

Text #3

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.5298. Min Act: -0.1697

Data Index: 1026216 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.4535. Min Act: -0.1700

Data Index: 1649562 (Python Code)

Max Activating Token Index: 332

Text #5

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.4662. Min Act: -0.1700

Data Index: 257358 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.4241. Min Act: -0.1700

Data Index: 187354 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.4108. Min Act: -0.1700

Data Index: 1207324 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.3941. Min Act: -0.1699

Data Index: 724640 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.3994. Min Act: -0.1700

Data Index: 367113 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.4161. Min Act: -0.1688

Data Index: 1183960 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.3692. Min Act: -0.1700

Data Index: 1437212 (Python Code)

Max Activating Token Index: 858

Text #12

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.3777. Min Act: -0.1699

Data Index: 1215867 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.3638. Min Act: -0.1699

Data Index: 1069508 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.3684. Min Act: -0.1700

Data Index: 235009 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.3648. Min Act: -0.1700

Data Index: 330797 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.3485. Min Act: -0.1699

Data Index: 1444607 (Python Code)

Max Activating Token Index: 1018

Text #17

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.3228. Min Act: -0.1700

Data Index: 609761 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.3516. Min Act: -0.1699

Data Index: 1196063 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.3099. Min Act: -0.1700

Data Index: 870144 (C4 (Web Text))

Max Activating Token Index: 985