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

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

Neuron 193 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: 3.4877. Min Range: -3.4877

Max Act: 3.4877. Min Act: -0.1700

Data Index: 1479251 (Python Code)

Max Activating Token Index: 485

Text #1

Max Range: 3.4877. Min Range: -3.4877

Max Act: 3.4355. Min Act: -0.1700

Data Index: 818217 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 3.4877. Min Range: -3.4877

Max Act: 3.4246. Min Act: -0.1700

Data Index: 1578368 (Python Code)

Max Activating Token Index: 385

Text #3

Max Range: 3.4877. Min Range: -3.4877

Max Act: 3.4103. Min Act: -0.1700

Data Index: 1438102 (Python Code)

Max Activating Token Index: 54

Text #4

Max Range: 3.4877. Min Range: -3.4877

Max Act: 3.3917. Min Act: -0.1700

Data Index: 1532737 (Python Code)

Max Activating Token Index: 580

Text #5

Max Range: 3.4877. Min Range: -3.4877

Max Act: 3.3744. Min Act: -0.1700

Data Index: 1622394 (Python Code)

Max Activating Token Index: 78

Text #6

Max Range: 3.4877. Min Range: -3.4877

Max Act: 3.3464. Min Act: -0.1700

Data Index: 487641 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 3.4877. Min Range: -3.4877

Max Act: 3.3127. Min Act: -0.1700

Data Index: 1622243 (Python Code)

Max Activating Token Index: 459

Text #8

Max Range: 3.4877. Min Range: -3.4877

Max Act: 3.3148. Min Act: -0.1700

Data Index: 488595 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 3.4877. Min Range: -3.4877

Max Act: 3.3052. Min Act: -0.1700

Data Index: 755745 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 3.4877. Min Range: -3.4877

Max Act: 3.2946. Min Act: -0.1700

Data Index: 948826 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 3.4877. Min Range: -3.4877

Max Act: 3.2826. Min Act: -0.1700

Data Index: 1612807 (Python Code)

Max Activating Token Index: 1001

Text #12

Max Range: 3.4877. Min Range: -3.4877

Max Act: 3.2641. Min Act: -0.1700

Data Index: 571172 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 3.4877. Min Range: -3.4877

Max Act: 3.2770. Min Act: -0.1700

Data Index: 1652452 (Python Code)

Max Activating Token Index: 159

Text #14

Max Range: 3.4877. Min Range: -3.4877

Max Act: 3.2425. Min Act: -0.1700

Data Index: 1100286 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 3.4877. Min Range: -3.4877

Max Act: 3.2349. Min Act: -0.1700

Data Index: 1554193 (Python Code)

Max Activating Token Index: 831

Text #16

Max Range: 3.4877. Min Range: -3.4877

Max Act: 3.2277. Min Act: -0.1700

Data Index: 1506810 (Python Code)

Max Activating Token Index: 808

Text #17

Max Range: 3.4877. Min Range: -3.4877

Max Act: 3.2555. Min Act: -0.1700

Data Index: 1499814 (Python Code)

Max Activating Token Index: 497

Text #18

Max Range: 3.4877. Min Range: -3.4877

Max Act: 3.2400. Min Act: -0.1700

Data Index: 1470967 (Python Code)

Max Activating Token Index: 260

Text #19

Max Range: 3.4877. Min Range: -3.4877

Max Act: 3.2199. Min Act: -0.1700

Data Index: 1637362 (Python Code)

Max Activating Token Index: 989