Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 618 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.6154. Min Range: -3.6154

Max Act: 3.6154. Min Act: -0.1700

Data Index: 129972 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 3.6154. Min Range: -3.6154

Max Act: 3.5058. Min Act: -0.1700

Data Index: 494059 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 3.6154. Min Range: -3.6154

Max Act: 3.4745. Min Act: -0.1700

Data Index: 1222885 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 3.6154. Min Range: -3.6154

Max Act: 3.4745. Min Act: -0.1700

Data Index: 1254583 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 3.6154. Min Range: -3.6154

Max Act: 3.3961. Min Act: -0.1700

Data Index: 1131811 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 3.6154. Min Range: -3.6154

Max Act: 3.3804. Min Act: -0.1700

Data Index: 286 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 3.6154. Min Range: -3.6154

Max Act: 3.3647. Min Act: -0.1700

Data Index: 4367 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 3.6154. Min Range: -3.6154

Max Act: 3.3490. Min Act: -0.1700

Data Index: 949047 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 3.6154. Min Range: -3.6154

Max Act: 3.3176. Min Act: -0.1700

Data Index: 547796 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 3.6154. Min Range: -3.6154

Max Act: 3.3333. Min Act: -0.1700

Data Index: 853427 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 3.6154. Min Range: -3.6154

Max Act: 3.3176. Min Act: -0.1700

Data Index: 413409 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 3.6154. Min Range: -3.6154

Max Act: 3.3019. Min Act: -0.1700

Data Index: 753944 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 3.6154. Min Range: -3.6154

Max Act: 3.3333. Min Act: -0.1700

Data Index: 617292 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 3.6154. Min Range: -3.6154

Max Act: 3.3176. Min Act: -0.1700

Data Index: 212608 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 3.6154. Min Range: -3.6154

Max Act: 3.3019. Min Act: -0.1700

Data Index: 906137 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 3.6154. Min Range: -3.6154

Max Act: 3.3019. Min Act: -0.1700

Data Index: 155661 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 3.6154. Min Range: -3.6154

Max Act: 3.3019. Min Act: -0.1700

Data Index: 962767 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 3.6154. Min Range: -3.6154

Max Act: 3.2862. Min Act: -0.1700

Data Index: 57950 (C4 (Web Text))

Max Activating Token Index: 563

Text #18

Max Range: 3.6154. Min Range: -3.6154

Max Act: 3.3019. Min Act: -0.1700

Data Index: 322608 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 3.6154. Min Range: -3.6154

Max Act: 3.2705. Min Act: -0.1700

Data Index: 1309746 (C4 (Web Text))

Max Activating Token Index: 518