Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5582 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1108. Min Range: -2.1108

Max Act: 1.9140. Min Act: -0.0000

Data Index: 1565536 (Python Code)

Max Activating Token Index: 683

Text #1

Max Range: 2.1108. Min Range: -2.1108

Max Act: 2.1108. Min Act: -0.0000

Data Index: 109019 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 2.1108. Min Range: -2.1108

Max Act: 1.8726. Min Act: -0.0000

Data Index: 1413012 (Python Code)

Max Activating Token Index: 689

Text #3

Max Range: 2.1108. Min Range: -2.1108

Max Act: 1.9671. Min Act: -0.0000

Data Index: 1383571 (Python Code)

Max Activating Token Index: 869

Text #4

Max Range: 2.1108. Min Range: -2.1108

Max Act: 1.7471. Min Act: -0.0000

Data Index: 754625 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 2.1108. Min Range: -2.1108

Max Act: 1.6994. Min Act: -0.0000

Data Index: 372808 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 2.1108. Min Range: -2.1108

Max Act: 1.6286. Min Act: -0.0000

Data Index: 239809 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 2.1108. Min Range: -2.1108

Max Act: 1.6002. Min Act: -0.0000

Data Index: 1565260 (Python Code)

Max Activating Token Index: 673

Text #8

Max Range: 2.1108. Min Range: -2.1108

Max Act: 1.5932. Min Act: -0.0000

Data Index: 184093 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 2.1108. Min Range: -2.1108

Max Act: 1.5920. Min Act: -0.0000

Data Index: 466131 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 2.1108. Min Range: -2.1108

Max Act: 1.5870. Min Act: -0.0000

Data Index: 1630531 (Python Code)

Max Activating Token Index: 250

Text #11

Max Range: 2.1108. Min Range: -2.1108

Max Act: 1.4974. Min Act: -0.0000

Data Index: 684608 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 2.1108. Min Range: -2.1108

Max Act: 1.5820. Min Act: -0.0000

Data Index: 1312398 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 2.1108. Min Range: -2.1108

Max Act: 1.4806. Min Act: -0.0000

Data Index: 194098 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 2.1108. Min Range: -2.1108

Max Act: 1.4624. Min Act: -0.0000

Data Index: 1884 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 2.1108. Min Range: -2.1108

Max Act: 1.4480. Min Act: -0.0000

Data Index: 407216 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 2.1108. Min Range: -2.1108

Max Act: 1.5060. Min Act: -0.0000

Data Index: 584007 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 2.1108. Min Range: -2.1108

Max Act: 1.4947. Min Act: -0.0000

Data Index: 178634 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 2.1108. Min Range: -2.1108

Max Act: 1.6667. Min Act: -0.0000

Data Index: 1362008 (Python Code)

Max Activating Token Index: 883

Text #19

Max Range: 2.1108. Min Range: -2.1108

Max Act: 1.4914. Min Act: -0.0000

Data Index: 1047511 (C4 (Web Text))

Max Activating Token Index: 580