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

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

Neuron 1461 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8674. Min Range: -3.8674

Max Act: 3.7560. Min Act: -0.0001

Data Index: 230898 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 3.8674. Min Range: -3.8674

Max Act: 3.8674. Min Act: -0.0001

Data Index: 287728 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 3.8674. Min Range: -3.8674

Max Act: 3.8137. Min Act: -0.0001

Data Index: 1227101 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 3.8674. Min Range: -3.8674

Max Act: 3.6623. Min Act: -0.0001

Data Index: 1090288 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 3.8674. Min Range: -3.8674

Max Act: 3.3068. Min Act: -0.0001

Data Index: 621204 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 3.8674. Min Range: -3.8674

Max Act: 3.3304. Min Act: -0.0001

Data Index: 939876 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 3.8674. Min Range: -3.8674

Max Act: 3.2441. Min Act: -0.0001

Data Index: 650382 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 3.8674. Min Range: -3.8674

Max Act: 3.2777. Min Act: -0.0001

Data Index: 705737 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 3.8674. Min Range: -3.8674

Max Act: 2.7400. Min Act: -0.0001

Data Index: 793718 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 3.8674. Min Range: -3.8674

Max Act: 2.9395. Min Act: -0.0001

Data Index: 1379181 (Python Code)

Max Activating Token Index: 88

Text #10

Max Range: 3.8674. Min Range: -3.8674

Max Act: 2.8599. Min Act: -0.0001

Data Index: 918157 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 3.8674. Min Range: -3.8674

Max Act: 2.7898. Min Act: -0.0001

Data Index: 309955 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 3.8674. Min Range: -3.8674

Max Act: 2.6238. Min Act: -0.0001

Data Index: 858852 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 3.8674. Min Range: -3.8674

Max Act: 2.8753. Min Act: -0.0001

Data Index: 326998 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 3.8674. Min Range: -3.8674

Max Act: 2.7189. Min Act: -0.0001

Data Index: 826837 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 3.8674. Min Range: -3.8674

Max Act: 2.7802. Min Act: -0.0001

Data Index: 226094 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 3.8674. Min Range: -3.8674

Max Act: 2.6311. Min Act: -0.0001

Data Index: 68695 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 3.8674. Min Range: -3.8674

Max Act: 2.6097. Min Act: -0.0001

Data Index: 9022 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 3.8674. Min Range: -3.8674

Max Act: 2.4537. Min Act: -0.0001

Data Index: 2186 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 3.8674. Min Range: -3.8674

Max Act: 2.4148. Min Act: -0.0001

Data Index: 1437196 (Python Code)

Max Activating Token Index: 278