Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2609 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0053. Min Range: -1.0053

Max Act: 1.0053. Min Act: -0.0001

Data Index: 1239929 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.9094. Min Act: -0.0001

Data Index: 342785 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.9202. Min Act: -0.0001

Data Index: 249547 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.8453. Min Act: -0.0001

Data Index: 634 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.8382. Min Act: -0.0001

Data Index: 9554 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.8342. Min Act: -0.0001

Data Index: 329606 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.8022. Min Act: -0.0001

Data Index: 1156665 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.8224. Min Act: -0.0001

Data Index: 250084 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7668. Min Act: -0.0001

Data Index: 1144969 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.8276. Min Act: -0.0001

Data Index: 650402 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.8054. Min Act: -0.0001

Data Index: 76237 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.8503. Min Act: -0.0001

Data Index: 835890 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7587. Min Act: -0.0001

Data Index: 173644 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7312. Min Act: -0.0001

Data Index: 529833 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.6277. Min Act: -0.0001

Data Index: 799265 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.6825. Min Act: -0.0001

Data Index: 548734 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7446. Min Act: -0.0001

Data Index: 852762 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.6740. Min Act: -0.0001

Data Index: 739037 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7252. Min Act: -0.0001

Data Index: 159735 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7621. Min Act: -0.0001

Data Index: 1330360 (C4 (Web Text))

Max Activating Token Index: 881