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

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

Neuron 2542 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: 2.3886. Min Range: -2.3886

Max Act: 2.3886. Min Act: -0.0002

Data Index: 200048 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 2.3886. Min Range: -2.3886

Max Act: 2.2618. Min Act: -0.0003

Data Index: 712864 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 2.3886. Min Range: -2.3886

Max Act: 2.1932. Min Act: -0.0002

Data Index: 554330 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 2.3886. Min Range: -2.3886

Max Act: 2.2257. Min Act: -0.0002

Data Index: 1127865 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 2.3886. Min Range: -2.3886

Max Act: 2.2431. Min Act: -0.0002

Data Index: 500512 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 2.3886. Min Range: -2.3886

Max Act: 2.1843. Min Act: -0.0002

Data Index: 1174086 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 2.3886. Min Range: -2.3886

Max Act: 2.1542. Min Act: -0.0002

Data Index: 919377 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 2.3886. Min Range: -2.3886

Max Act: 2.1705. Min Act: -0.0002

Data Index: 144100 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 2.3886. Min Range: -2.3886

Max Act: 2.1464. Min Act: -0.0002

Data Index: 701036 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 2.3886. Min Range: -2.3886

Max Act: 2.0865. Min Act: -0.0002

Data Index: 612247 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 2.3886. Min Range: -2.3886

Max Act: 2.1817. Min Act: -0.0002

Data Index: 116111 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 2.3886. Min Range: -2.3886

Max Act: 2.1327. Min Act: -0.0002

Data Index: 222016 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 2.3886. Min Range: -2.3886

Max Act: 2.1234. Min Act: -0.0002

Data Index: 389408 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 2.3886. Min Range: -2.3886

Max Act: 2.0546. Min Act: -0.0002

Data Index: 993362 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 2.3886. Min Range: -2.3886

Max Act: 2.1714. Min Act: -0.0002

Data Index: 339815 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 2.3886. Min Range: -2.3886

Max Act: 2.1055. Min Act: -0.0002

Data Index: 488622 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 2.3886. Min Range: -2.3886

Max Act: 2.0942. Min Act: -0.0002

Data Index: 528667 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 2.3886. Min Range: -2.3886

Max Act: 2.0950. Min Act: -0.0002

Data Index: 563495 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 2.3886. Min Range: -2.3886

Max Act: 2.0591. Min Act: -0.0002

Data Index: 717014 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 2.3886. Min Range: -2.3886

Max Act: 2.0638. Min Act: -0.0002

Data Index: 313489 (C4 (Web Text))

Max Activating Token Index: 699