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

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

Neuron 5569 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: 2.4983. Min Range: -2.4983

Max Act: 2.4983. Min Act: -0.0002

Data Index: 745905 (C4 (Web Text))

Max Activating Token Index: 534

Text #1

Max Range: 2.4983. Min Range: -2.4983

Max Act: 2.4651. Min Act: -0.0002

Data Index: 532200 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 2.4983. Min Range: -2.4983

Max Act: 2.4465. Min Act: -0.0003

Data Index: 740305 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 2.4983. Min Range: -2.4983

Max Act: 2.4416. Min Act: -0.0002

Data Index: 1058652 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 2.4983. Min Range: -2.4983

Max Act: 2.4504. Min Act: -0.0002

Data Index: 972238 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 2.4983. Min Range: -2.4983

Max Act: 2.4249. Min Act: -0.0002

Data Index: 315152 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 2.4983. Min Range: -2.4983

Max Act: 2.4181. Min Act: -0.0003

Data Index: 88087 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 2.4983. Min Range: -2.4983

Max Act: 2.4181. Min Act: -0.0002

Data Index: 647495 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 2.4983. Min Range: -2.4983

Max Act: 2.3881. Min Act: -0.0002

Data Index: 1161860 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 2.4983. Min Range: -2.4983

Max Act: 2.2971. Min Act: -0.0002

Data Index: 616981 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 2.4983. Min Range: -2.4983

Max Act: 2.2894. Min Act: -0.0003

Data Index: 708639 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 2.4983. Min Range: -2.4983

Max Act: 2.3236. Min Act: -0.0002

Data Index: 664698 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 2.4983. Min Range: -2.4983

Max Act: 2.2937. Min Act: -0.0002

Data Index: 797350 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 2.4983. Min Range: -2.4983

Max Act: 2.3287. Min Act: -0.0002

Data Index: 985928 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 2.4983. Min Range: -2.4983

Max Act: 2.3235. Min Act: -0.0002

Data Index: 386191 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 2.4983. Min Range: -2.4983

Max Act: 2.2593. Min Act: -0.0002

Data Index: 761388 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 2.4983. Min Range: -2.4983

Max Act: 2.2882. Min Act: -0.0002

Data Index: 896751 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 2.4983. Min Range: -2.4983

Max Act: 2.3400. Min Act: -0.0002

Data Index: 501900 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 2.4983. Min Range: -2.4983

Max Act: 2.3076. Min Act: -0.0002

Data Index: 1005705 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 2.4983. Min Range: -2.4983

Max Act: 2.2749. Min Act: -0.0002

Data Index: 952236 (C4 (Web Text))

Max Activating Token Index: 857