Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4361 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.6522. Min Act: -0.0000

Data Index: 490674 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.6671. Min Act: -0.0000

Data Index: 99578 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.6071. Min Act: -0.0000

Data Index: 1213537 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.5037. Min Act: -0.0000

Data Index: 430990 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4856. Min Act: -0.0000

Data Index: 382116 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4709. Min Act: -0.0000

Data Index: 1207204 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.5004. Min Act: -0.0000

Data Index: 1381017 (Python Code)

Max Activating Token Index: 159

Text #7

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4654. Min Act: -0.0000

Data Index: 424223 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4322. Min Act: -0.0000

Data Index: 1023483 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4521. Min Act: -0.0000

Data Index: 950090 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4320. Min Act: -0.0000

Data Index: 201056 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4243. Min Act: -0.0000

Data Index: 900167 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4025. Min Act: -0.0000

Data Index: 1420164 (Python Code)

Max Activating Token Index: 621

Text #13

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4347. Min Act: -0.0000

Data Index: 1420852 (Python Code)

Max Activating Token Index: 933

Text #14

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4486. Min Act: -0.0000

Data Index: 201923 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4007. Min Act: -0.0000

Data Index: 91548 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4357. Min Act: -0.0000

Data Index: 1591923 (Python Code)

Max Activating Token Index: 761

Text #17

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4186. Min Act: -0.0000

Data Index: 1125453 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.3820. Min Act: -0.0000

Data Index: 1501882 (Python Code)

Max Activating Token Index: 534

Text #19

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4143. Min Act: -0.0000

Data Index: 1474559 (Python Code)

Max Activating Token Index: 817