Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3091 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.1116. Min Range: -3.1116

Max Act: 3.1116. Min Act: -0.0001

Data Index: 604424 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.6440. Min Act: -0.0001

Data Index: 1078032 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.5867. Min Act: -0.0001

Data Index: 263740 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.6837. Min Act: -0.0001

Data Index: 1084300 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.5079. Min Act: -0.0001

Data Index: 1131125 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.6227. Min Act: -0.0001

Data Index: 322600 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.4944. Min Act: -0.0001

Data Index: 1279673 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.4920. Min Act: -0.0001

Data Index: 438760 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.4443. Min Act: -0.0001

Data Index: 93052 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.4390. Min Act: -0.0001

Data Index: 1311731 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.4337. Min Act: -0.0001

Data Index: 409658 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.3133. Min Act: -0.0001

Data Index: 977160 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.3359. Min Act: -0.0001

Data Index: 366751 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.4091. Min Act: -0.0001

Data Index: 171592 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.3787. Min Act: -0.0001

Data Index: 310156 (C4 (Web Text))

Max Activating Token Index: 886

Text #15

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.2522. Min Act: -0.0001

Data Index: 459032 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.3450. Min Act: -0.0001

Data Index: 1061531 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.3653. Min Act: -0.0001

Data Index: 1126339 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.2118. Min Act: -0.0001

Data Index: 543428 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.1939. Min Act: -0.0001

Data Index: 406152 (C4 (Web Text))

Max Activating Token Index: 81