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

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

Neuron 2023 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3202. Min Range: -1.3202

Max Act: 1.3202. Min Act: -0.0000

Data Index: 398184 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 1.3202. Min Range: -1.3202

Max Act: 0.7893. Min Act: -0.0000

Data Index: 283799 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 1.3202. Min Range: -1.3202

Max Act: 1.0457. Min Act: -0.0000

Data Index: 402435 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 1.3202. Min Range: -1.3202

Max Act: 0.9532. Min Act: -0.0000

Data Index: 1133583 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 1.3202. Min Range: -1.3202

Max Act: 0.9263. Min Act: -0.0000

Data Index: 193200 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 1.3202. Min Range: -1.3202

Max Act: 0.9887. Min Act: -0.0000

Data Index: 1002087 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 1.3202. Min Range: -1.3202

Max Act: 0.8973. Min Act: -0.0000

Data Index: 235962 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 1.3202. Min Range: -1.3202

Max Act: 1.0784. Min Act: -0.0000

Data Index: 1062857 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 1.3202. Min Range: -1.3202

Max Act: 0.9449. Min Act: -0.0000

Data Index: 728155 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 1.3202. Min Range: -1.3202

Max Act: 0.8010. Min Act: -0.0000

Data Index: 1290746 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 1.3202. Min Range: -1.3202

Max Act: 0.8907. Min Act: -0.0000

Data Index: 316935 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 1.3202. Min Range: -1.3202

Max Act: 0.8666. Min Act: -0.0000

Data Index: 580466 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 1.3202. Min Range: -1.3202

Max Act: 0.8816. Min Act: -0.0000

Data Index: 898665 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 1.3202. Min Range: -1.3202

Max Act: 0.8528. Min Act: -0.0000

Data Index: 499632 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 1.3202. Min Range: -1.3202

Max Act: 0.8248. Min Act: -0.0000

Data Index: 1058864 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 1.3202. Min Range: -1.3202

Max Act: 0.8179. Min Act: -0.0000

Data Index: 183412 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 1.3202. Min Range: -1.3202

Max Act: 0.8475. Min Act: -0.0000

Data Index: 432063 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 1.3202. Min Range: -1.3202

Max Act: 0.9535. Min Act: -0.0000

Data Index: 855345 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 1.3202. Min Range: -1.3202

Max Act: 0.8073. Min Act: -0.0000

Data Index: 1307823 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 1.3202. Min Range: -1.3202

Max Act: 0.8668. Min Act: -0.0000

Data Index: 699798 (C4 (Web Text))

Max Activating Token Index: 717