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

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

Neuron 3036 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: 0.5107. Min Range: -0.5107

Max Act: 0.5107. Min Act: -0.0003

Data Index: 947257 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4964. Min Act: -0.0003

Data Index: 1044054 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4761. Min Act: -0.0003

Data Index: 800107 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4924. Min Act: -0.0003

Data Index: 484390 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4897. Min Act: -0.0003

Data Index: 540603 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4877. Min Act: -0.0003

Data Index: 551636 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4841. Min Act: -0.0003

Data Index: 159998 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4834. Min Act: -0.0003

Data Index: 658442 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4636. Min Act: -0.0003

Data Index: 936339 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4662. Min Act: -0.0003

Data Index: 997370 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4940. Min Act: -0.0003

Data Index: 1144210 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4631. Min Act: -0.0003

Data Index: 1126220 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4982. Min Act: -0.0003

Data Index: 208359 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4570. Min Act: -0.0003

Data Index: 571378 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4422. Min Act: -0.0003

Data Index: 942571 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4764. Min Act: -0.0003

Data Index: 302934 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4673. Min Act: -0.0003

Data Index: 650918 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4701. Min Act: -0.0003

Data Index: 867439 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4419. Min Act: -0.0003

Data Index: 112600 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4488. Min Act: -0.0003

Data Index: 954595 (C4 (Web Text))

Max Activating Token Index: 654