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

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

Neuron 3671 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1129. Min Range: -1.1129

Max Act: 1.0802. Min Act: -0.0001

Data Index: 797828 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 1.1129. Min Range: -1.1129

Max Act: 1.1129. Min Act: -0.0001

Data Index: 598369 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 1.1129. Min Range: -1.1129

Max Act: 1.1114. Min Act: -0.0001

Data Index: 792263 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 1.1129. Min Range: -1.1129

Max Act: 1.0011. Min Act: -0.0001

Data Index: 1127949 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 1.1129. Min Range: -1.1129

Max Act: 1.0585. Min Act: -0.0001

Data Index: 1050252 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.9933. Min Act: -0.0001

Data Index: 97510 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 1.1129. Min Range: -1.1129

Max Act: 1.0095. Min Act: -0.0001

Data Index: 1017648 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.8663. Min Act: -0.0001

Data Index: 907799 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.9224. Min Act: -0.0001

Data Index: 1211082 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.9470. Min Act: -0.0001

Data Index: 382591 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.9565. Min Act: -0.0001

Data Index: 1306691 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.8929. Min Act: -0.0001

Data Index: 980589 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.8865. Min Act: -0.0001

Data Index: 135171 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.8916. Min Act: -0.0001

Data Index: 615425 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.8322. Min Act: -0.0001

Data Index: 1472019 (Python Code)

Max Activating Token Index: 432

Text #15

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.9168. Min Act: -0.0000

Data Index: 92640 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.9404. Min Act: -0.0001

Data Index: 403173 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.9051. Min Act: -0.0000

Data Index: 657855 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.8816. Min Act: -0.0001

Data Index: 1033678 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.9302. Min Act: -0.0001

Data Index: 688225 (C4 (Web Text))

Max Activating Token Index: 101