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

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

Neuron 1188 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: 3.5166. Min Range: -3.5166

Max Act: 3.5166. Min Act: -0.1700

Data Index: 1517634 (Python Code)

Max Activating Token Index: 23

Text #1

Max Range: 3.5166. Min Range: -3.5166

Max Act: 3.4853. Min Act: -0.1700

Data Index: 1643431 (Python Code)

Max Activating Token Index: 774

Text #2

Max Range: 3.5166. Min Range: -3.5166

Max Act: 3.4853. Min Act: -0.1700

Data Index: 1412673 (Python Code)

Max Activating Token Index: 443

Text #3

Max Range: 3.5166. Min Range: -3.5166

Max Act: 3.4382. Min Act: -0.1700

Data Index: 1606437 (Python Code)

Max Activating Token Index: 9

Text #4

Max Range: 3.5166. Min Range: -3.5166

Max Act: 3.4226. Min Act: -0.1700

Data Index: 1611845 (Python Code)

Max Activating Token Index: 759

Text #5

Max Range: 3.5166. Min Range: -3.5166

Max Act: 3.4069. Min Act: -0.1700

Data Index: 1379948 (Python Code)

Max Activating Token Index: 74

Text #6

Max Range: 3.5166. Min Range: -3.5166

Max Act: 3.4069. Min Act: -0.1700

Data Index: 1493585 (Python Code)

Max Activating Token Index: 498

Text #7

Max Range: 3.5166. Min Range: -3.5166

Max Act: 3.3912. Min Act: -0.1700

Data Index: 1478239 (Python Code)

Max Activating Token Index: 571

Text #8

Max Range: 3.5166. Min Range: -3.5166

Max Act: 3.3598. Min Act: -0.1700

Data Index: 1470088 (Python Code)

Max Activating Token Index: 756

Text #9

Max Range: 3.5166. Min Range: -3.5166

Max Act: 3.3441. Min Act: -0.1700

Data Index: 1652623 (Python Code)

Max Activating Token Index: 43

Text #10

Max Range: 3.5166. Min Range: -3.5166

Max Act: 3.3598. Min Act: -0.1700

Data Index: 1459352 (Python Code)

Max Activating Token Index: 93

Text #11

Max Range: 3.5166. Min Range: -3.5166

Max Act: 3.3441. Min Act: -0.1700

Data Index: 1555812 (Python Code)

Max Activating Token Index: 861

Text #12

Max Range: 3.5166. Min Range: -3.5166

Max Act: 3.3441. Min Act: -0.1700

Data Index: 1632353 (Python Code)

Max Activating Token Index: 47

Text #13

Max Range: 3.5166. Min Range: -3.5166

Max Act: 3.3441. Min Act: -0.1700

Data Index: 1418301 (Python Code)

Max Activating Token Index: 161

Text #14

Max Range: 3.5166. Min Range: -3.5166

Max Act: 3.3284. Min Act: -0.1700

Data Index: 1633067 (Python Code)

Max Activating Token Index: 60

Text #15

Max Range: 3.5166. Min Range: -3.5166

Max Act: 3.3284. Min Act: -0.1700

Data Index: 1475120 (Python Code)

Max Activating Token Index: 92

Text #16

Max Range: 3.5166. Min Range: -3.5166

Max Act: 3.3441. Min Act: -0.1700

Data Index: 1492038 (Python Code)

Max Activating Token Index: 815

Text #17

Max Range: 3.5166. Min Range: -3.5166

Max Act: 3.3284. Min Act: -0.1700

Data Index: 1421273 (Python Code)

Max Activating Token Index: 13

Text #18

Max Range: 3.5166. Min Range: -3.5166

Max Act: 3.3127. Min Act: -0.1700

Data Index: 1576514 (Python Code)

Max Activating Token Index: 206

Text #19

Max Range: 3.5166. Min Range: -3.5166

Max Act: 3.3284. Min Act: -0.1700

Data Index: 1403304 (Python Code)

Max Activating Token Index: 731