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

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

Neuron 1563 in Layer 0

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: 0.4983. Min Range: -0.4983

Max Act: 0.4913. Min Act: -0.0001

Data Index: 631470 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.4983. Min Act: -0.0001

Data Index: 259164 (C4 (Web Text))

Max Activating Token Index: 225

Text #2

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.4903. Min Act: -0.0001

Data Index: 546847 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.4804. Min Act: -0.0001

Data Index: 1013756 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.4760. Min Act: -0.0001

Data Index: 1307899 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.4336. Min Act: -0.0001

Data Index: 1350714 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.4235. Min Act: -0.0001

Data Index: 836136 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.4094. Min Act: -0.0001

Data Index: 743454 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.4040. Min Act: -0.0001

Data Index: 1053033 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.4100. Min Act: -0.0001

Data Index: 304031 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.4064. Min Act: -0.0001

Data Index: 1236527 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.3992. Min Act: -0.0001

Data Index: 168327 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.3802. Min Act: -0.0001

Data Index: 181406 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.3705. Min Act: -0.0001

Data Index: 175448 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.3672. Min Act: -0.0001

Data Index: 1357775 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.3461. Min Act: -0.0001

Data Index: 255809 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.3517. Min Act: -0.0001

Data Index: 117627 (C4 (Web Text))

Max Activating Token Index: 311

Text #17

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.3497. Min Act: -0.0001

Data Index: 318027 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.3482. Min Act: -0.0001

Data Index: 341011 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.3491. Min Act: -0.0001

Data Index: 1108593 (C4 (Web Text))

Max Activating Token Index: 762