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

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

Neuron 1257 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: 3.9610. Min Range: -3.9610

Max Act: 3.9610. Min Act: -0.1700

Data Index: 320637 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.8985. Min Act: -0.1700

Data Index: 309623 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.8985. Min Act: -0.1700

Data Index: 219763 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.8046. Min Act: -0.1700

Data Index: 1197286 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.7734. Min Act: -0.1700

Data Index: 801774 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.7734. Min Act: -0.1700

Data Index: 1181143 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.7421. Min Act: -0.1700

Data Index: 153991 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.7108. Min Act: -0.1700

Data Index: 621345 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.7108. Min Act: -0.1700

Data Index: 1126417 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.7108. Min Act: -0.1700

Data Index: 502444 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.6482. Min Act: -0.1700

Data Index: 371271 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.6795. Min Act: -0.1700

Data Index: 1059464 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.6795. Min Act: -0.1700

Data Index: 198447 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.6795. Min Act: -0.1700

Data Index: 521811 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.7108. Min Act: -0.1700

Data Index: 611306 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.6795. Min Act: -0.1700

Data Index: 727035 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.7421. Min Act: -0.1700

Data Index: 755075 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.6795. Min Act: -0.1700

Data Index: 788879 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.6795. Min Act: -0.1700

Data Index: 253072 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.6795. Min Act: -0.1700

Data Index: 850407 (C4 (Web Text))

Max Activating Token Index: 398