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

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

Neuron 2002 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: 3.4493. Min Range: -3.4493

Max Act: 3.4443. Min Act: -0.1700

Data Index: 1477803 (Python Code)

Max Activating Token Index: 325

Text #1

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.4278. Min Act: -0.1700

Data Index: 1515104 (Python Code)

Max Activating Token Index: 1016

Text #2

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.4493. Min Act: -0.1700

Data Index: 1604667 (Python Code)

Max Activating Token Index: 619

Text #3

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.4320. Min Act: -0.1700

Data Index: 1371414 (Python Code)

Max Activating Token Index: 294

Text #4

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.3830. Min Act: -0.1700

Data Index: 1514939 (Python Code)

Max Activating Token Index: 859

Text #5

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.3952. Min Act: -0.1700

Data Index: 1629150 (Python Code)

Max Activating Token Index: 55

Text #6

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.3843. Min Act: -0.1700

Data Index: 1443661 (Python Code)

Max Activating Token Index: 81

Text #7

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.3795. Min Act: -0.1700

Data Index: 1421786 (Python Code)

Max Activating Token Index: 410

Text #8

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.3273. Min Act: -0.1700

Data Index: 1608076 (Python Code)

Max Activating Token Index: 770

Text #9

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.3411. Min Act: -0.1700

Data Index: 1448620 (Python Code)

Max Activating Token Index: 212

Text #10

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.3193. Min Act: -0.1700

Data Index: 1591659 (Python Code)

Max Activating Token Index: 177

Text #11

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.3285. Min Act: -0.1700

Data Index: 1655376 (Python Code)

Max Activating Token Index: 928

Text #12

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.3281. Min Act: -0.1700

Data Index: 1418402 (Python Code)

Max Activating Token Index: 800

Text #13

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.3080. Min Act: -0.1700

Data Index: 1593041 (Python Code)

Max Activating Token Index: 1009

Text #14

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.2996. Min Act: -0.1700

Data Index: 1535590 (Python Code)

Max Activating Token Index: 353

Text #15

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.3115. Min Act: -0.1700

Data Index: 1495022 (Python Code)

Max Activating Token Index: 801

Text #16

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.3243. Min Act: -0.1700

Data Index: 1444658 (Python Code)

Max Activating Token Index: 245

Text #17

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.3032. Min Act: -0.1700

Data Index: 1572596 (Python Code)

Max Activating Token Index: 505

Text #18

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.2865. Min Act: -0.1700

Data Index: 1406401 (Python Code)

Max Activating Token Index: 482

Text #19

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.2843. Min Act: -0.1700

Data Index: 1414187 (Python Code)

Max Activating Token Index: 317