Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2391 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.5647. Min Act: -0.0003

Data Index: 1112606 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.5956. Min Act: -0.0003

Data Index: 915269 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.5420. Min Act: -0.0003

Data Index: 99517 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.5091. Min Act: -0.0003

Data Index: 6761 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4937. Min Act: -0.0003

Data Index: 36940 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4987. Min Act: -0.0003

Data Index: 1010907 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4916. Min Act: -0.0003

Data Index: 358082 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4548. Min Act: -0.0003

Data Index: 230834 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4998. Min Act: -0.0003

Data Index: 631023 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4573. Min Act: -0.0003

Data Index: 304175 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4379. Min Act: -0.0003

Data Index: 571930 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4412. Min Act: -0.0003

Data Index: 1248767 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4787. Min Act: -0.0003

Data Index: 667539 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.3896. Min Act: -0.0003

Data Index: 1099022 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4409. Min Act: -0.0003

Data Index: 630988 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4002. Min Act: -0.0003

Data Index: 263026 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.3791. Min Act: -0.0003

Data Index: 814034 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4180. Min Act: -0.0003

Data Index: 43436 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4317. Min Act: -0.0003

Data Index: 562852 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4056. Min Act: -0.0003

Data Index: 979854 (C4 (Web Text))

Max Activating Token Index: 377