Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 439 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.4113. Min Range: -3.4113

Max Act: 3.4113. Min Act: -0.1700

Data Index: 1081876 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 3.4113. Min Range: -3.4113

Max Act: 3.4113. Min Act: -0.1700

Data Index: 176137 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 3.4113. Min Range: -3.4113

Max Act: 3.3957. Min Act: -0.1700

Data Index: 1127405 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 3.4113. Min Range: -3.4113

Max Act: 3.3643. Min Act: -0.1700

Data Index: 661944 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 3.4113. Min Range: -3.4113

Max Act: 3.3643. Min Act: -0.1700

Data Index: 28589 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 3.4113. Min Range: -3.4113

Max Act: 3.3643. Min Act: -0.1700

Data Index: 402959 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 3.4113. Min Range: -3.4113

Max Act: 3.3486. Min Act: -0.1700

Data Index: 6634 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 3.4113. Min Range: -3.4113

Max Act: 3.3486. Min Act: -0.1700

Data Index: 1342051 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 3.4113. Min Range: -3.4113

Max Act: 3.3486. Min Act: -0.1700

Data Index: 484938 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 3.4113. Min Range: -3.4113

Max Act: 3.3486. Min Act: -0.1700

Data Index: 1133974 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 3.4113. Min Range: -3.4113

Max Act: 3.3172. Min Act: -0.1700

Data Index: 392091 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 3.4113. Min Range: -3.4113

Max Act: 3.3172. Min Act: -0.1700

Data Index: 1211145 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 3.4113. Min Range: -3.4113

Max Act: 3.3329. Min Act: -0.1700

Data Index: 395190 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 3.4113. Min Range: -3.4113

Max Act: 3.3172. Min Act: -0.1700

Data Index: 628782 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 3.4113. Min Range: -3.4113

Max Act: 3.3486. Min Act: -0.1700

Data Index: 255528 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 3.4113. Min Range: -3.4113

Max Act: 3.3329. Min Act: -0.1700

Data Index: 1356586 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 3.4113. Min Range: -3.4113

Max Act: 3.3015. Min Act: -0.1700

Data Index: 392991 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 3.4113. Min Range: -3.4113

Max Act: 3.3172. Min Act: -0.1700

Data Index: 905478 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 3.4113. Min Range: -3.4113

Max Act: 3.3172. Min Act: -0.1700

Data Index: 842417 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 3.4113. Min Range: -3.4113

Max Act: 3.2858. Min Act: -0.1700

Data Index: 167026 (C4 (Web Text))

Max Activating Token Index: 59