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

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

Neuron 5132 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.4711. Min Range: -2.4711

Max Act: 2.4711. Min Act: -0.0002

Data Index: 1320824 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 2.4711. Min Range: -2.4711

Max Act: 2.1891. Min Act: -0.0003

Data Index: 623483 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.8738. Min Act: -0.0002

Data Index: 1305051 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.9070. Min Act: -0.0002

Data Index: 539456 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.8385. Min Act: -0.0002

Data Index: 522021 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.7816. Min Act: -0.0002

Data Index: 1193129 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.7430. Min Act: -0.0002

Data Index: 840268 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.7523. Min Act: -0.0002

Data Index: 985572 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.7146. Min Act: -0.0002

Data Index: 164127 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.6552. Min Act: -0.0003

Data Index: 1358664 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.6564. Min Act: -0.0002

Data Index: 189732 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.6523. Min Act: -0.0002

Data Index: 601454 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.6467. Min Act: -0.0002

Data Index: 948091 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.6289. Min Act: -0.0002

Data Index: 1248260 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.6481. Min Act: -0.0002

Data Index: 539683 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.6157. Min Act: -0.0002

Data Index: 158280 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.6490. Min Act: -0.0002

Data Index: 1132714 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.5950. Min Act: -0.0002

Data Index: 580981 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.6368. Min Act: -0.0002

Data Index: 515480 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.6236. Min Act: -0.0002

Data Index: 385445 (C4 (Web Text))

Max Activating Token Index: 415