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

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

Neuron 1905 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: 3.3682. Min Range: -3.3682

Max Act: 3.3275. Min Act: -0.1700

Data Index: 503716 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 3.3682. Min Range: -3.3682

Max Act: 3.3682. Min Act: -0.1700

Data Index: 1567367 (Python Code)

Max Activating Token Index: 593

Text #2

Max Range: 3.3682. Min Range: -3.3682

Max Act: 3.3417. Min Act: -0.1700

Data Index: 1380392 (Python Code)

Max Activating Token Index: 81

Text #3

Max Range: 3.3682. Min Range: -3.3682

Max Act: 3.3335. Min Act: -0.1700

Data Index: 1633880 (Python Code)

Max Activating Token Index: 990

Text #4

Max Range: 3.3682. Min Range: -3.3682

Max Act: 3.3311. Min Act: -0.1700

Data Index: 1404981 (Python Code)

Max Activating Token Index: 881

Text #5

Max Range: 3.3682. Min Range: -3.3682

Max Act: 3.3046. Min Act: -0.1700

Data Index: 1439792 (Python Code)

Max Activating Token Index: 468

Text #6

Max Range: 3.3682. Min Range: -3.3682

Max Act: 3.2690. Min Act: -0.1700

Data Index: 587157 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 3.3682. Min Range: -3.3682

Max Act: 3.2669. Min Act: -0.1700

Data Index: 1424520 (Python Code)

Max Activating Token Index: 97

Text #8

Max Range: 3.3682. Min Range: -3.3682

Max Act: 3.2423. Min Act: -0.1700

Data Index: 290006 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 3.3682. Min Range: -3.3682

Max Act: 3.2766. Min Act: -0.1700

Data Index: 1527664 (Python Code)

Max Activating Token Index: 523

Text #10

Max Range: 3.3682. Min Range: -3.3682

Max Act: 3.2548. Min Act: -0.1700

Data Index: 1510687 (Python Code)

Max Activating Token Index: 175

Text #11

Max Range: 3.3682. Min Range: -3.3682

Max Act: 3.2314. Min Act: -0.1700

Data Index: 940739 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 3.3682. Min Range: -3.3682

Max Act: 3.1939. Min Act: -0.1700

Data Index: 1552326 (Python Code)

Max Activating Token Index: 916

Text #13

Max Range: 3.3682. Min Range: -3.3682

Max Act: 3.2385. Min Act: -0.1700

Data Index: 1591150 (Python Code)

Max Activating Token Index: 389

Text #14

Max Range: 3.3682. Min Range: -3.3682

Max Act: 3.2241. Min Act: -0.1700

Data Index: 1567062 (Python Code)

Max Activating Token Index: 835

Text #15

Max Range: 3.3682. Min Range: -3.3682

Max Act: 3.1982. Min Act: -0.1700

Data Index: 576167 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 3.3682. Min Range: -3.3682

Max Act: 3.2238. Min Act: -0.1700

Data Index: 1585660 (Python Code)

Max Activating Token Index: 180

Text #17

Max Range: 3.3682. Min Range: -3.3682

Max Act: 3.2056. Min Act: -0.1700

Data Index: 1567118 (Python Code)

Max Activating Token Index: 171

Text #18

Max Range: 3.3682. Min Range: -3.3682

Max Act: 3.2166. Min Act: -0.1700

Data Index: 1655991 (Python Code)

Max Activating Token Index: 507

Text #19

Max Range: 3.3682. Min Range: -3.3682

Max Act: 3.1876. Min Act: -0.1700

Data Index: 1576800 (Python Code)

Max Activating Token Index: 1011