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

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

Neuron 2103 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.8256. Min Act: -0.0001

Data Index: 1237792 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.8939. Min Act: -0.0001

Data Index: 87123 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.6921. Min Act: -0.0001

Data Index: 1357586 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.7485. Min Act: -0.0001

Data Index: 522479 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.6990. Min Act: -0.0001

Data Index: 899581 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.6889. Min Act: -0.0001

Data Index: 727378 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.6196. Min Act: -0.0001

Data Index: 310988 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.6238. Min Act: -0.0001

Data Index: 823427 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.6630. Min Act: -0.0001

Data Index: 1211376 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.6390. Min Act: -0.0001

Data Index: 1031939 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.5665. Min Act: -0.0001

Data Index: 915793 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.6137. Min Act: -0.0001

Data Index: 932651 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.6136. Min Act: -0.0001

Data Index: 99057 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.6277. Min Act: -0.0001

Data Index: 219162 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.6086. Min Act: -0.0001

Data Index: 618359 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.5873. Min Act: -0.0001

Data Index: 337968 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.6029. Min Act: -0.0001

Data Index: 667620 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.6195. Min Act: -0.0001

Data Index: 1164537 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.6041. Min Act: -0.0001

Data Index: 1212111 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.5976. Min Act: -0.0001

Data Index: 660486 (C4 (Web Text))

Max Activating Token Index: 284