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

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

Neuron 2464 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: 1.9060. Min Range: -1.9060

Max Act: 1.9060. Min Act: -0.0001

Data Index: 970646 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.9033. Min Act: -0.0001

Data Index: 200810 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.8784. Min Act: -0.0001

Data Index: 872712 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.7301. Min Act: -0.0001

Data Index: 147232 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.8272. Min Act: -0.0001

Data Index: 1091320 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.8145. Min Act: -0.0001

Data Index: 180262 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.8009. Min Act: -0.0001

Data Index: 368742 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.8286. Min Act: -0.0001

Data Index: 681072 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.6992. Min Act: -0.0001

Data Index: 476018 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.7395. Min Act: -0.0001

Data Index: 270811 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.7278. Min Act: -0.0001

Data Index: 1267392 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.7268. Min Act: -0.0001

Data Index: 1152921 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.7573. Min Act: -0.0001

Data Index: 1562523 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.6830. Min Act: -0.0001

Data Index: 1018197 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.7588. Min Act: -0.0001

Data Index: 515412 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.6093. Min Act: -0.0001

Data Index: 1012452 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.6495. Min Act: -0.0001

Data Index: 908188 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.6087. Min Act: -0.0001

Data Index: 301804 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.6712. Min Act: -0.0001

Data Index: 818372 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.5757. Min Act: -0.0001

Data Index: 1034456 (C4 (Web Text))

Max Activating Token Index: 733