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

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

Neuron 255 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: 3.7581. Min Range: -3.7581

Max Act: 3.7581. Min Act: -0.1700

Data Index: 1330702 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 3.7581. Min Range: -3.7581

Max Act: 3.6107. Min Act: -0.1700

Data Index: 965293 (C4 (Web Text))

Max Activating Token Index: 624

Text #2

Max Range: 3.7581. Min Range: -3.7581

Max Act: 3.5521. Min Act: -0.1700

Data Index: 1503811 (Python Code)

Max Activating Token Index: 610

Text #3

Max Range: 3.7581. Min Range: -3.7581

Max Act: 3.5534. Min Act: -0.1700

Data Index: 1239767 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 3.7581. Min Range: -3.7581

Max Act: 3.5418. Min Act: -0.1700

Data Index: 1239234 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 3.7581. Min Range: -3.7581

Max Act: 3.4745. Min Act: -0.1700

Data Index: 403744 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 3.7581. Min Range: -3.7581

Max Act: 3.5258. Min Act: -0.1700

Data Index: 1403683 (Python Code)

Max Activating Token Index: 698

Text #7

Max Range: 3.7581. Min Range: -3.7581

Max Act: 3.5282. Min Act: -0.1700

Data Index: 1412376 (Python Code)

Max Activating Token Index: 642

Text #8

Max Range: 3.7581. Min Range: -3.7581

Max Act: 3.5348. Min Act: -0.1700

Data Index: 1056830 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 3.7581. Min Range: -3.7581

Max Act: 3.5042. Min Act: -0.1700

Data Index: 1564658 (Python Code)

Max Activating Token Index: 697

Text #10

Max Range: 3.7581. Min Range: -3.7581

Max Act: 3.4983. Min Act: -0.1700

Data Index: 1503902 (Python Code)

Max Activating Token Index: 639

Text #11

Max Range: 3.7581. Min Range: -3.7581

Max Act: 3.4694. Min Act: -0.1700

Data Index: 1465910 (Python Code)

Max Activating Token Index: 467

Text #12

Max Range: 3.7581. Min Range: -3.7581

Max Act: 3.4334. Min Act: -0.1700

Data Index: 254673 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 3.7581. Min Range: -3.7581

Max Act: 3.4855. Min Act: -0.1700

Data Index: 151500 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 3.7581. Min Range: -3.7581

Max Act: 3.4650. Min Act: -0.1700

Data Index: 541329 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 3.7581. Min Range: -3.7581

Max Act: 3.4396. Min Act: -0.1700

Data Index: 1520605 (Python Code)

Max Activating Token Index: 261

Text #16

Max Range: 3.7581. Min Range: -3.7581

Max Act: 3.4879. Min Act: -0.1700

Data Index: 1040401 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 3.7581. Min Range: -3.7581

Max Act: 3.4217. Min Act: -0.1700

Data Index: 1511489 (Python Code)

Max Activating Token Index: 304

Text #18

Max Range: 3.7581. Min Range: -3.7581

Max Act: 3.4202. Min Act: -0.1700

Data Index: 1645977 (Python Code)

Max Activating Token Index: 941

Text #19

Max Range: 3.7581. Min Range: -3.7581

Max Act: 3.4370. Min Act: -0.1700

Data Index: 1256024 (C4 (Web Text))

Max Activating Token Index: 71