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

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

Neuron 54 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3942. Min Range: -1.3942

Max Act: 1.3902. Min Act: -0.0002

Data Index: 232712 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 1.3942. Min Range: -1.3942

Max Act: 1.3942. Min Act: -0.0001

Data Index: 615013 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 1.3942. Min Range: -1.3942

Max Act: 1.3043. Min Act: -0.0001

Data Index: 716793 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 1.3942. Min Range: -1.3942

Max Act: 1.2562. Min Act: -0.0001

Data Index: 250781 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 1.3942. Min Range: -1.3942

Max Act: 1.2872. Min Act: -0.0002

Data Index: 241594 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 1.3942. Min Range: -1.3942

Max Act: 1.1368. Min Act: -0.0001

Data Index: 394715 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 1.3942. Min Range: -1.3942

Max Act: 1.2483. Min Act: -0.0002

Data Index: 236532 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 1.3942. Min Range: -1.3942

Max Act: 1.1624. Min Act: -0.0001

Data Index: 889748 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 1.3942. Min Range: -1.3942

Max Act: 1.2648. Min Act: -0.0001

Data Index: 448334 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 1.3942. Min Range: -1.3942

Max Act: 1.2192. Min Act: -0.0001

Data Index: 832013 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 1.3942. Min Range: -1.3942

Max Act: 1.0803. Min Act: -0.0002

Data Index: 934069 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 1.3942. Min Range: -1.3942

Max Act: 1.0247. Min Act: -0.0002

Data Index: 44007 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 1.3942. Min Range: -1.3942

Max Act: 0.9884. Min Act: -0.0002

Data Index: 315964 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 1.3942. Min Range: -1.3942

Max Act: 1.1273. Min Act: -0.0001

Data Index: 645895 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 1.3942. Min Range: -1.3942

Max Act: 1.0988. Min Act: -0.0002

Data Index: 1012424 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 1.3942. Min Range: -1.3942

Max Act: 1.0296. Min Act: -0.0001

Data Index: 1219435 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 1.3942. Min Range: -1.3942

Max Act: 1.1619. Min Act: -0.0001

Data Index: 1205721 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 1.3942. Min Range: -1.3942

Max Act: 1.2084. Min Act: -0.0001

Data Index: 155674 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 1.3942. Min Range: -1.3942

Max Act: 1.1729. Min Act: -0.0001

Data Index: 753002 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 1.3942. Min Range: -1.3942

Max Act: 1.1705. Min Act: -0.0001

Data Index: 263043 (C4 (Web Text))

Max Activating Token Index: 547