Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1117 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4785. Min Range: -1.4785

Max Act: 1.4785. Min Act: -0.0002

Data Index: 545290 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 1.4785. Min Range: -1.4785

Max Act: 1.1053. Min Act: -0.0002

Data Index: 1359850 (Python Code)

Max Activating Token Index: 148

Text #2

Max Range: 1.4785. Min Range: -1.4785

Max Act: 1.1040. Min Act: -0.0002

Data Index: 1552363 (Python Code)

Max Activating Token Index: 109

Text #3

Max Range: 1.4785. Min Range: -1.4785

Max Act: 1.0991. Min Act: -0.0002

Data Index: 1298822 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 1.4785. Min Range: -1.4785

Max Act: 1.0516. Min Act: -0.0002

Data Index: 1520000 (Python Code)

Max Activating Token Index: 956

Text #5

Max Range: 1.4785. Min Range: -1.4785

Max Act: 1.0023. Min Act: -0.0002

Data Index: 852354 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 1.4785. Min Range: -1.4785

Max Act: 1.0450. Min Act: -0.0002

Data Index: 1259166 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 1.4785. Min Range: -1.4785

Max Act: 0.9792. Min Act: -0.0002

Data Index: 731027 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 1.4785. Min Range: -1.4785

Max Act: 0.9559. Min Act: -0.0002

Data Index: 1078864 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 1.4785. Min Range: -1.4785

Max Act: 0.9799. Min Act: -0.0002

Data Index: 212144 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 1.4785. Min Range: -1.4785

Max Act: 0.9516. Min Act: -0.0002

Data Index: 1505230 (Python Code)

Max Activating Token Index: 30

Text #11

Max Range: 1.4785. Min Range: -1.4785

Max Act: 0.9332. Min Act: -0.0002

Data Index: 1145650 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 1.4785. Min Range: -1.4785

Max Act: 0.9294. Min Act: -0.0002

Data Index: 721637 (C4 (Web Text))

Max Activating Token Index: 861

Text #13

Max Range: 1.4785. Min Range: -1.4785

Max Act: 0.9270. Min Act: -0.0002

Data Index: 1505212 (Python Code)

Max Activating Token Index: 71

Text #14

Max Range: 1.4785. Min Range: -1.4785

Max Act: 0.9195. Min Act: -0.0002

Data Index: 1003652 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 1.4785. Min Range: -1.4785

Max Act: 0.9115. Min Act: -0.0002

Data Index: 529945 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 1.4785. Min Range: -1.4785

Max Act: 0.9079. Min Act: -0.0002

Data Index: 1156281 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 1.4785. Min Range: -1.4785

Max Act: 0.9069. Min Act: -0.0002

Data Index: 758284 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 1.4785. Min Range: -1.4785

Max Act: 0.8990. Min Act: -0.0002

Data Index: 726973 (C4 (Web Text))

Max Activating Token Index: 831

Text #19

Max Range: 1.4785. Min Range: -1.4785

Max Act: 0.8981. Min Act: -0.0002

Data Index: 1401845 (Python Code)

Max Activating Token Index: 562