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

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

Neuron 1169 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5975. Min Range: -3.5975

Max Act: 3.5975. Min Act: -0.1700

Data Index: 503126 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 3.5975. Min Range: -3.5975

Max Act: 3.5035. Min Act: -0.1700

Data Index: 869072 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 3.5975. Min Range: -3.5975

Max Act: 3.4565. Min Act: -0.1700

Data Index: 713050 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 3.5975. Min Range: -3.5975

Max Act: 3.4565. Min Act: -0.1700

Data Index: 323991 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 3.5975. Min Range: -3.5975

Max Act: 3.4095. Min Act: -0.1700

Data Index: 200715 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 3.5975. Min Range: -3.5975

Max Act: 3.4408. Min Act: -0.1700

Data Index: 464790 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 3.5975. Min Range: -3.5975

Max Act: 3.4565. Min Act: -0.1700

Data Index: 74518 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 3.5975. Min Range: -3.5975

Max Act: 3.4095. Min Act: -0.1700

Data Index: 393186 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 3.5975. Min Range: -3.5975

Max Act: 3.3938. Min Act: -0.1700

Data Index: 1110254 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 3.5975. Min Range: -3.5975

Max Act: 3.4251. Min Act: -0.1700

Data Index: 507729 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 3.5975. Min Range: -3.5975

Max Act: 3.4095. Min Act: -0.1700

Data Index: 1208530 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 3.5975. Min Range: -3.5975

Max Act: 3.4251. Min Act: -0.1700

Data Index: 137887 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 3.5975. Min Range: -3.5975

Max Act: 3.3781. Min Act: -0.1700

Data Index: 71940 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 3.5975. Min Range: -3.5975

Max Act: 3.3938. Min Act: -0.1700

Data Index: 775871 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 3.5975. Min Range: -3.5975

Max Act: 3.3781. Min Act: -0.1700

Data Index: 318000 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 3.5975. Min Range: -3.5975

Max Act: 3.4095. Min Act: -0.1700

Data Index: 559481 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 3.5975. Min Range: -3.5975

Max Act: 3.3938. Min Act: -0.1700

Data Index: 613665 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 3.5975. Min Range: -3.5975

Max Act: 3.4095. Min Act: -0.1700

Data Index: 632087 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 3.5975. Min Range: -3.5975

Max Act: 3.3781. Min Act: -0.1700

Data Index: 268767 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 3.5975. Min Range: -3.5975

Max Act: 3.3624. Min Act: -0.1700

Data Index: 897949 (C4 (Web Text))

Max Activating Token Index: 978