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

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

Neuron 1098 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0347. Min Range: -1.0347

Max Act: 0.9815. Min Act: -0.0000

Data Index: 201262 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 1.0347. Min Range: -1.0347

Max Act: 0.9686. Min Act: -0.0000

Data Index: 646538 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 1.0347. Min Range: -1.0347

Max Act: 1.0347. Min Act: -0.0000

Data Index: 1134173 (C4 (Web Text))

Max Activating Token Index: 977

Text #3

Max Range: 1.0347. Min Range: -1.0347

Max Act: 1.0096. Min Act: -0.0000

Data Index: 1185736 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 1.0347. Min Range: -1.0347

Max Act: 0.9432. Min Act: -0.0001

Data Index: 1355576 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 1.0347. Min Range: -1.0347

Max Act: 0.7866. Min Act: -0.0001

Data Index: 91896 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 1.0347. Min Range: -1.0347

Max Act: 0.8452. Min Act: -0.0001

Data Index: 727479 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 1.0347. Min Range: -1.0347

Max Act: 0.8659. Min Act: -0.0000

Data Index: 544411 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 1.0347. Min Range: -1.0347

Max Act: 0.8933. Min Act: -0.0001

Data Index: 362195 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 1.0347. Min Range: -1.0347

Max Act: 0.8622. Min Act: -0.0001

Data Index: 1135903 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 1.0347. Min Range: -1.0347

Max Act: 0.8223. Min Act: -0.0001

Data Index: 546345 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 1.0347. Min Range: -1.0347

Max Act: 0.8515. Min Act: -0.0001

Data Index: 694310 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 1.0347. Min Range: -1.0347

Max Act: 0.8167. Min Act: -0.0001

Data Index: 284754 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 1.0347. Min Range: -1.0347

Max Act: 0.8244. Min Act: -0.0001

Data Index: 212072 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 1.0347. Min Range: -1.0347

Max Act: 0.7950. Min Act: -0.0000

Data Index: 197845 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 1.0347. Min Range: -1.0347

Max Act: 0.8185. Min Act: -0.0000

Data Index: 1084372 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 1.0347. Min Range: -1.0347

Max Act: 0.8076. Min Act: -0.0000

Data Index: 531489 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 1.0347. Min Range: -1.0347

Max Act: 0.7863. Min Act: -0.0000

Data Index: 1129787 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 1.0347. Min Range: -1.0347

Max Act: 0.8043. Min Act: -0.0001

Data Index: 760685 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 1.0347. Min Range: -1.0347

Max Act: 0.7566. Min Act: -0.0001

Data Index: 526064 (C4 (Web Text))

Max Activating Token Index: 975