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

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

Neuron 1996 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: 7.1458. Min Range: -7.1458

Max Act: 7.1442. Min Act: -0.1700

Data Index: 146907 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 7.1458. Min Range: -7.1458

Max Act: 7.1458. Min Act: -0.1700

Data Index: 877701 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 7.1458. Min Range: -7.1458

Max Act: 7.1146. Min Act: -0.1700

Data Index: 425678 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 7.1458. Min Range: -7.1458

Max Act: 7.0302. Min Act: -0.1700

Data Index: 551254 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 7.1458. Min Range: -7.1458

Max Act: 6.9874. Min Act: -0.1700

Data Index: 753303 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 7.1458. Min Range: -7.1458

Max Act: 6.9769. Min Act: -0.1700

Data Index: 1294446 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 7.1458. Min Range: -7.1458

Max Act: 6.9872. Min Act: -0.1700

Data Index: 779102 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 7.1458. Min Range: -7.1458

Max Act: 6.9705. Min Act: -0.1700

Data Index: 98316 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 7.1458. Min Range: -7.1458

Max Act: 6.7806. Min Act: -0.1700

Data Index: 1484224 (Python Code)

Max Activating Token Index: 1000

Text #9

Max Range: 7.1458. Min Range: -7.1458

Max Act: 6.7858. Min Act: -0.1700

Data Index: 635012 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 7.1458. Min Range: -7.1458

Max Act: 6.8014. Min Act: -0.1700

Data Index: 356309 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 7.1458. Min Range: -7.1458

Max Act: 6.7534. Min Act: -0.1700

Data Index: 728219 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 7.1458. Min Range: -7.1458

Max Act: 6.7435. Min Act: -0.1700

Data Index: 255382 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 7.1458. Min Range: -7.1458

Max Act: 6.7028. Min Act: -0.1700

Data Index: 682277 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 7.1458. Min Range: -7.1458

Max Act: 6.7104. Min Act: -0.1119

Data Index: 833778 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 7.1458. Min Range: -7.1458

Max Act: 6.6553. Min Act: -0.1700

Data Index: 1092513 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 7.1458. Min Range: -7.1458

Max Act: 6.6053. Min Act: -0.1700

Data Index: 238998 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 7.1458. Min Range: -7.1458

Max Act: 6.6170. Min Act: -0.1700

Data Index: 1071118 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 7.1458. Min Range: -7.1458

Max Act: 6.5923. Min Act: -0.1700

Data Index: 1507376 (Python Code)

Max Activating Token Index: 354

Text #19

Max Range: 7.1458. Min Range: -7.1458

Max Act: 6.6215. Min Act: -0.1700

Data Index: 161769 (C4 (Web Text))

Max Activating Token Index: 337