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

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

Neuron 381 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: 3.0226. Min Range: -3.0226

Max Act: 3.0226. Min Act: -0.1700

Data Index: 1599614 (Python Code)

Max Activating Token Index: 907

Text #1

Max Range: 3.0226. Min Range: -3.0226

Max Act: 2.9939. Min Act: -0.1700

Data Index: 1572688 (Python Code)

Max Activating Token Index: 484

Text #2

Max Range: 3.0226. Min Range: -3.0226

Max Act: 2.9767. Min Act: -0.1700

Data Index: 1579633 (Python Code)

Max Activating Token Index: 773

Text #3

Max Range: 3.0226. Min Range: -3.0226

Max Act: 2.9017. Min Act: -0.1700

Data Index: 227001 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 3.0226. Min Range: -3.0226

Max Act: 2.8957. Min Act: -0.1700

Data Index: 1566329 (Python Code)

Max Activating Token Index: 74

Text #5

Max Range: 3.0226. Min Range: -3.0226

Max Act: 2.8861. Min Act: -0.1700

Data Index: 117626 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 3.0226. Min Range: -3.0226

Max Act: 2.8729. Min Act: -0.1700

Data Index: 1540506 (Python Code)

Max Activating Token Index: 338

Text #7

Max Range: 3.0226. Min Range: -3.0226

Max Act: 2.9056. Min Act: -0.1700

Data Index: 1144523 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 3.0226. Min Range: -3.0226

Max Act: 2.8691. Min Act: -0.1700

Data Index: 1501679 (Python Code)

Max Activating Token Index: 877

Text #9

Max Range: 3.0226. Min Range: -3.0226

Max Act: 2.8708. Min Act: -0.1700

Data Index: 1130251 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 3.0226. Min Range: -3.0226

Max Act: 2.8663. Min Act: -0.1700

Data Index: 279948 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 3.0226. Min Range: -3.0226

Max Act: 2.8602. Min Act: -0.1700

Data Index: 1430546 (Python Code)

Max Activating Token Index: 46

Text #12

Max Range: 3.0226. Min Range: -3.0226

Max Act: 2.8360. Min Act: -0.1700

Data Index: 1255449 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 3.0226. Min Range: -3.0226

Max Act: 2.8293. Min Act: -0.1700

Data Index: 388165 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 3.0226. Min Range: -3.0226

Max Act: 2.8393. Min Act: -0.1700

Data Index: 484622 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 3.0226. Min Range: -3.0226

Max Act: 2.8130. Min Act: -0.1700

Data Index: 526803 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 3.0226. Min Range: -3.0226

Max Act: 2.8083. Min Act: -0.1700

Data Index: 1567956 (Python Code)

Max Activating Token Index: 79

Text #17

Max Range: 3.0226. Min Range: -3.0226

Max Act: 2.8208. Min Act: -0.1700

Data Index: 1551349 (Python Code)

Max Activating Token Index: 921

Text #18

Max Range: 3.0226. Min Range: -3.0226

Max Act: 2.8170. Min Act: -0.1700

Data Index: 1368699 (Python Code)

Max Activating Token Index: 958

Text #19

Max Range: 3.0226. Min Range: -3.0226

Max Act: 2.7963. Min Act: -0.1700

Data Index: 1444911 (Python Code)

Max Activating Token Index: 342