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

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

Neuron 1163 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.2856. Min Act: -0.1700

Data Index: 1626863 (Python Code)

Max Activating Token Index: 574

Text #1

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.2384. Min Act: -0.1700

Data Index: 1575355 (Python Code)

Max Activating Token Index: 901

Text #2

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.2227. Min Act: -0.1700

Data Index: 1367390 (Python Code)

Max Activating Token Index: 11

Text #3

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.2227. Min Act: -0.1700

Data Index: 1376215 (Python Code)

Max Activating Token Index: 514

Text #4

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.2070. Min Act: -0.1700

Data Index: 1523217 (Python Code)

Max Activating Token Index: 754

Text #5

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.1755. Min Act: -0.1700

Data Index: 1636530 (Python Code)

Max Activating Token Index: 151

Text #6

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.1755. Min Act: -0.1700

Data Index: 1382990 (Python Code)

Max Activating Token Index: 673

Text #7

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.1598. Min Act: -0.1700

Data Index: 1614216 (Python Code)

Max Activating Token Index: 851

Text #8

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.1125. Min Act: -0.1700

Data Index: 1595769 (Python Code)

Max Activating Token Index: 356

Text #9

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.1283. Min Act: -0.1700

Data Index: 1395481 (Python Code)

Max Activating Token Index: 505

Text #10

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.0967. Min Act: -0.1700

Data Index: 1470433 (Python Code)

Max Activating Token Index: 162

Text #11

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.0810. Min Act: -0.1700

Data Index: 1655178 (Python Code)

Max Activating Token Index: 883

Text #12

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.0810. Min Act: -0.1700

Data Index: 1495958 (Python Code)

Max Activating Token Index: 226

Text #13

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.0967. Min Act: -0.1700

Data Index: 1533235 (Python Code)

Max Activating Token Index: 86

Text #14

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.0494. Min Act: -0.1700

Data Index: 1524897 (Python Code)

Max Activating Token Index: 141

Text #15

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.0336. Min Act: -0.1700

Data Index: 1600754 (Python Code)

Max Activating Token Index: 6

Text #16

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.0178. Min Act: -0.1700

Data Index: 1425496 (Python Code)

Max Activating Token Index: 950

Text #17

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.0178. Min Act: -0.1700

Data Index: 1361220 (Python Code)

Max Activating Token Index: 633

Text #18

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.0178. Min Act: -0.1700

Data Index: 1502152 (Python Code)

Max Activating Token Index: 107

Text #19

Max Range: 3.2856. Min Range: -3.2856

Max Act: 2.9704. Min Act: -0.1700

Data Index: 1503662 (Python Code)

Max Activating Token Index: 80