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

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

Neuron 868 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: 3.4440. Min Range: -3.4440

Max Act: 3.4397. Min Act: -0.1700

Data Index: 1550408 (Python Code)

Max Activating Token Index: 819

Text #1

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.4440. Min Act: -0.1700

Data Index: 1480586 (Python Code)

Max Activating Token Index: 183

Text #2

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.3672. Min Act: -0.1700

Data Index: 1642997 (Python Code)

Max Activating Token Index: 393

Text #3

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.3553. Min Act: -0.1700

Data Index: 1557121 (Python Code)

Max Activating Token Index: 58

Text #4

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.3361. Min Act: -0.1700

Data Index: 1618114 (Python Code)

Max Activating Token Index: 59

Text #5

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.3334. Min Act: -0.1700

Data Index: 370401 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.3066. Min Act: -0.1700

Data Index: 1545751 (Python Code)

Max Activating Token Index: 199

Text #7

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.3184. Min Act: -0.1700

Data Index: 1220881 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.3097. Min Act: -0.1700

Data Index: 325882 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.2911. Min Act: -0.1700

Data Index: 709606 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.2689. Min Act: -0.1700

Data Index: 1595372 (Python Code)

Max Activating Token Index: 600

Text #11

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.2677. Min Act: -0.1700

Data Index: 268897 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.2729. Min Act: -0.1700

Data Index: 847454 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.2796. Min Act: -0.1700

Data Index: 1486072 (Python Code)

Max Activating Token Index: 400

Text #14

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.2355. Min Act: -0.1700

Data Index: 1433412 (Python Code)

Max Activating Token Index: 62

Text #15

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.2450. Min Act: -0.1700

Data Index: 687165 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.2556. Min Act: -0.1700

Data Index: 1457975 (Python Code)

Max Activating Token Index: 358

Text #17

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.2386. Min Act: -0.1700

Data Index: 964352 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.2330. Min Act: -0.1700

Data Index: 920640 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.2413. Min Act: -0.1700

Data Index: 822859 (C4 (Web Text))

Max Activating Token Index: 508