Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1563 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.5650. Min Act: -0.0001

Data Index: 1040592 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.6796. Min Act: -0.0001

Data Index: 396020 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.5768. Min Act: -0.0001

Data Index: 841700 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.6236. Min Act: -0.0001

Data Index: 1135342 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.5057. Min Act: -0.0001

Data Index: 464093 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.5882. Min Act: -0.0001

Data Index: 378401 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.5278. Min Act: -0.0001

Data Index: 1146183 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.5307. Min Act: -0.0001

Data Index: 809427 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.4344. Min Act: -0.0001

Data Index: 758405 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.5550. Min Act: -0.0001

Data Index: 991769 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.5407. Min Act: -0.0001

Data Index: 91823 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.5707. Min Act: -0.0001

Data Index: 1266970 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.5249. Min Act: -0.0001

Data Index: 207409 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.5425. Min Act: -0.0001

Data Index: 644967 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.4477. Min Act: -0.0001

Data Index: 1300417 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.4595. Min Act: -0.0001

Data Index: 1000149 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.4841. Min Act: -0.0001

Data Index: 735056 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.3686. Min Act: -0.0001

Data Index: 526183 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.5338. Min Act: -0.0001

Data Index: 197036 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.5243. Min Act: -0.0001

Data Index: 1331273 (C4 (Web Text))

Max Activating Token Index: 427