Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 839 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.5529. Min Range: -5.5529

Max Act: 5.5529. Min Act: -0.1700

Data Index: 1609381 (Python Code)

Max Activating Token Index: 270

Text #1

Max Range: 5.5529. Min Range: -5.5529

Max Act: 5.5217. Min Act: -0.1700

Data Index: 1603911 (Python Code)

Max Activating Token Index: 286

Text #2

Max Range: 5.5529. Min Range: -5.5529

Max Act: 5.4904. Min Act: -0.1700

Data Index: 1374741 (Python Code)

Max Activating Token Index: 244

Text #3

Max Range: 5.5529. Min Range: -5.5529

Max Act: 5.4904. Min Act: -0.1700

Data Index: 1455653 (Python Code)

Max Activating Token Index: 120

Text #4

Max Range: 5.5529. Min Range: -5.5529

Max Act: 5.4592. Min Act: -0.1700

Data Index: 1616421 (Python Code)

Max Activating Token Index: 272

Text #5

Max Range: 5.5529. Min Range: -5.5529

Max Act: 5.4592. Min Act: -0.1700

Data Index: 1364912 (Python Code)

Max Activating Token Index: 131

Text #6

Max Range: 5.5529. Min Range: -5.5529

Max Act: 5.4592. Min Act: -0.1700

Data Index: 1460730 (Python Code)

Max Activating Token Index: 407

Text #7

Max Range: 5.5529. Min Range: -5.5529

Max Act: 5.4279. Min Act: -0.1700

Data Index: 1644216 (Python Code)

Max Activating Token Index: 317

Text #8

Max Range: 5.5529. Min Range: -5.5529

Max Act: 5.4592. Min Act: -0.1700

Data Index: 1487788 (Python Code)

Max Activating Token Index: 438

Text #9

Max Range: 5.5529. Min Range: -5.5529

Max Act: 5.4279. Min Act: -0.1700

Data Index: 1605333 (Python Code)

Max Activating Token Index: 155

Text #10

Max Range: 5.5529. Min Range: -5.5529

Max Act: 5.4279. Min Act: -0.1700

Data Index: 1462964 (Python Code)

Max Activating Token Index: 434

Text #11

Max Range: 5.5529. Min Range: -5.5529

Max Act: 5.4592. Min Act: -0.1700

Data Index: 1626175 (Python Code)

Max Activating Token Index: 236

Text #12

Max Range: 5.5529. Min Range: -5.5529

Max Act: 5.3967. Min Act: -0.1700

Data Index: 1609495 (Python Code)

Max Activating Token Index: 229

Text #13

Max Range: 5.5529. Min Range: -5.5529

Max Act: 5.4279. Min Act: -0.1700

Data Index: 1486980 (Python Code)

Max Activating Token Index: 272

Text #14

Max Range: 5.5529. Min Range: -5.5529

Max Act: 5.3967. Min Act: -0.1700

Data Index: 1390042 (Python Code)

Max Activating Token Index: 809

Text #15

Max Range: 5.5529. Min Range: -5.5529

Max Act: 5.3967. Min Act: -0.1700

Data Index: 1479005 (Python Code)

Max Activating Token Index: 250

Text #16

Max Range: 5.5529. Min Range: -5.5529

Max Act: 5.3654. Min Act: -0.1700

Data Index: 1377832 (Python Code)

Max Activating Token Index: 120

Text #17

Max Range: 5.5529. Min Range: -5.5529

Max Act: 5.3654. Min Act: -0.1700

Data Index: 1592930 (Python Code)

Max Activating Token Index: 100

Text #18

Max Range: 5.5529. Min Range: -5.5529

Max Act: 5.3654. Min Act: -0.1700

Data Index: 1416519 (Python Code)

Max Activating Token Index: 179

Text #19

Max Range: 5.5529. Min Range: -5.5529

Max Act: 5.3967. Min Act: -0.1700

Data Index: 1593251 (Python Code)

Max Activating Token Index: 20