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

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

Neuron 1372 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: 3.6950. Min Range: -3.6950

Max Act: 3.6950. Min Act: -0.1700

Data Index: 1650555 (Python Code)

Max Activating Token Index: 92

Text #1

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.6573. Min Act: -0.1700

Data Index: 1574693 (Python Code)

Max Activating Token Index: 472

Text #2

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.6472. Min Act: -0.1700

Data Index: 1486955 (Python Code)

Max Activating Token Index: 373

Text #3

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.6395. Min Act: -0.1700

Data Index: 1620114 (Python Code)

Max Activating Token Index: 156

Text #4

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.6453. Min Act: -0.1700

Data Index: 1421926 (Python Code)

Max Activating Token Index: 659

Text #5

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.6409. Min Act: -0.1700

Data Index: 1544764 (Python Code)

Max Activating Token Index: 618

Text #6

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.6232. Min Act: -0.1700

Data Index: 1562175 (Python Code)

Max Activating Token Index: 999

Text #7

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.6158. Min Act: -0.1700

Data Index: 1390983 (Python Code)

Max Activating Token Index: 405

Text #8

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.6152. Min Act: -0.1700

Data Index: 1584455 (Python Code)

Max Activating Token Index: 681

Text #9

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.6174. Min Act: -0.1700

Data Index: 1385822 (Python Code)

Max Activating Token Index: 986

Text #10

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.6208. Min Act: -0.1700

Data Index: 1417458 (Python Code)

Max Activating Token Index: 465

Text #11

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.6240. Min Act: -0.1700

Data Index: 1491617 (Python Code)

Max Activating Token Index: 41

Text #12

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.6055. Min Act: -0.1700

Data Index: 1525130 (Python Code)

Max Activating Token Index: 725

Text #13

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.6073. Min Act: -0.1700

Data Index: 1441318 (Python Code)

Max Activating Token Index: 365

Text #14

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.6065. Min Act: -0.1700

Data Index: 1530220 (Python Code)

Max Activating Token Index: 576

Text #15

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.6161. Min Act: -0.1700

Data Index: 1475389 (Python Code)

Max Activating Token Index: 213

Text #16

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.5977. Min Act: -0.1700

Data Index: 1580154 (Python Code)

Max Activating Token Index: 384

Text #17

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.6000. Min Act: -0.1700

Data Index: 1583888 (Python Code)

Max Activating Token Index: 342

Text #18

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.6060. Min Act: -0.1700

Data Index: 1366142 (Python Code)

Max Activating Token Index: 382

Text #19

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.6152. Min Act: -0.1700

Data Index: 1525522 (Python Code)

Max Activating Token Index: 792