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

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

Neuron 1249 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: 2.9409. Min Range: -2.9409

Max Act: 2.9409. Min Act: -0.1700

Data Index: 549963 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 2.9409. Min Range: -2.9409

Max Act: 2.9019. Min Act: -0.1700

Data Index: 1214109 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 2.9409. Min Range: -2.9409

Max Act: 2.8852. Min Act: -0.1700

Data Index: 441206 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 2.9409. Min Range: -2.9409

Max Act: 2.8886. Min Act: -0.1700

Data Index: 931426 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 2.9409. Min Range: -2.9409

Max Act: 2.8773. Min Act: -0.1700

Data Index: 63928 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 2.9409. Min Range: -2.9409

Max Act: 2.8701. Min Act: -0.1700

Data Index: 312655 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 2.9409. Min Range: -2.9409

Max Act: 2.8563. Min Act: -0.1700

Data Index: 494545 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 2.9409. Min Range: -2.9409

Max Act: 2.8569. Min Act: -0.1700

Data Index: 1277284 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 2.9409. Min Range: -2.9409

Max Act: 2.8432. Min Act: -0.1700

Data Index: 856937 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 2.9409. Min Range: -2.9409

Max Act: 2.8339. Min Act: -0.1700

Data Index: 508694 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 2.9409. Min Range: -2.9409

Max Act: 2.8499. Min Act: -0.1700

Data Index: 691344 (C4 (Web Text))

Max Activating Token Index: 439

Text #11

Max Range: 2.9409. Min Range: -2.9409

Max Act: 2.8404. Min Act: -0.1700

Data Index: 1074990 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 2.9409. Min Range: -2.9409

Max Act: 2.8215. Min Act: -0.1700

Data Index: 523686 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 2.9409. Min Range: -2.9409

Max Act: 2.8278. Min Act: -0.1700

Data Index: 1106397 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 2.9409. Min Range: -2.9409

Max Act: 2.8305. Min Act: -0.1700

Data Index: 213321 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 2.9409. Min Range: -2.9409

Max Act: 2.8214. Min Act: -0.1700

Data Index: 181500 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 2.9409. Min Range: -2.9409

Max Act: 2.8074. Min Act: -0.1700

Data Index: 775380 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 2.9409. Min Range: -2.9409

Max Act: 2.8132. Min Act: -0.1700

Data Index: 1014740 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 2.9409. Min Range: -2.9409

Max Act: 2.8038. Min Act: -0.1700

Data Index: 426029 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 2.9409. Min Range: -2.9409

Max Act: 2.8036. Min Act: -0.1699

Data Index: 629383 (C4 (Web Text))

Max Activating Token Index: 366