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

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

Neuron 584 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: 4.4114. Min Range: -4.4114

Max Act: 4.4114. Min Act: -0.1700

Data Index: 1580026 (Python Code)

Max Activating Token Index: 574

Text #1

Max Range: 4.4114. Min Range: -4.4114

Max Act: 4.3347. Min Act: -0.1700

Data Index: 1541218 (Python Code)

Max Activating Token Index: 892

Text #2

Max Range: 4.4114. Min Range: -4.4114

Max Act: 4.3064. Min Act: -0.1700

Data Index: 1517811 (Python Code)

Max Activating Token Index: 436

Text #3

Max Range: 4.4114. Min Range: -4.4114

Max Act: 4.2850. Min Act: -0.1700

Data Index: 1366313 (Python Code)

Max Activating Token Index: 679

Text #4

Max Range: 4.4114. Min Range: -4.4114

Max Act: 4.2069. Min Act: -0.1700

Data Index: 1400059 (Python Code)

Max Activating Token Index: 570

Text #5

Max Range: 4.4114. Min Range: -4.4114

Max Act: 4.0610. Min Act: -0.1700

Data Index: 1605715 (Python Code)

Max Activating Token Index: 112

Text #6

Max Range: 4.4114. Min Range: -4.4114

Max Act: 4.0195. Min Act: -0.1700

Data Index: 1503046 (Python Code)

Max Activating Token Index: 278

Text #7

Max Range: 4.4114. Min Range: -4.4114

Max Act: 4.0273. Min Act: -0.1700

Data Index: 1528109 (Python Code)

Max Activating Token Index: 758

Text #8

Max Range: 4.4114. Min Range: -4.4114

Max Act: 3.9892. Min Act: -0.1700

Data Index: 1512478 (Python Code)

Max Activating Token Index: 666

Text #9

Max Range: 4.4114. Min Range: -4.4114

Max Act: 3.9797. Min Act: -0.1700

Data Index: 1406659 (Python Code)

Max Activating Token Index: 643

Text #10

Max Range: 4.4114. Min Range: -4.4114

Max Act: 3.9556. Min Act: -0.1700

Data Index: 1462624 (Python Code)

Max Activating Token Index: 171

Text #11

Max Range: 4.4114. Min Range: -4.4114

Max Act: 3.9278. Min Act: -0.1700

Data Index: 1585446 (Python Code)

Max Activating Token Index: 769

Text #12

Max Range: 4.4114. Min Range: -4.4114

Max Act: 3.9325. Min Act: -0.1700

Data Index: 1621177 (Python Code)

Max Activating Token Index: 140

Text #13

Max Range: 4.4114. Min Range: -4.4114

Max Act: 3.9097. Min Act: -0.1700

Data Index: 1441806 (Python Code)

Max Activating Token Index: 153

Text #14

Max Range: 4.4114. Min Range: -4.4114

Max Act: 3.9066. Min Act: -0.1700

Data Index: 1372938 (Python Code)

Max Activating Token Index: 965

Text #15

Max Range: 4.4114. Min Range: -4.4114

Max Act: 3.8701. Min Act: -0.1700

Data Index: 1490421 (Python Code)

Max Activating Token Index: 312

Text #16

Max Range: 4.4114. Min Range: -4.4114

Max Act: 3.8521. Min Act: -0.1700

Data Index: 1402580 (Python Code)

Max Activating Token Index: 738

Text #17

Max Range: 4.4114. Min Range: -4.4114

Max Act: 3.8408. Min Act: -0.1700

Data Index: 1367678 (Python Code)

Max Activating Token Index: 249

Text #18

Max Range: 4.4114. Min Range: -4.4114

Max Act: 3.8307. Min Act: -0.1700

Data Index: 1507036 (Python Code)

Max Activating Token Index: 525

Text #19

Max Range: 4.4114. Min Range: -4.4114

Max Act: 3.8146. Min Act: -0.1700

Data Index: 1407234 (Python Code)

Max Activating Token Index: 638