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

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

Neuron 672 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.7132. Min Act: 0.0000

Data Index: 1217992 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.6182. Min Act: -0.0001

Data Index: 369026 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.5981. Min Act: -0.0000

Data Index: 348937 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.6296. Min Act: -0.0000

Data Index: 371388 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.5941. Min Act: -0.0000

Data Index: 471152 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.5942. Min Act: -0.0000

Data Index: 421407 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.5685. Min Act: -0.0001

Data Index: 673037 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.5979. Min Act: -0.0000

Data Index: 1250355 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.5803. Min Act: -0.0000

Data Index: 825093 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.5774. Min Act: -0.0000

Data Index: 1332657 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.5662. Min Act: -0.0001

Data Index: 997121 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.5660. Min Act: -0.0000

Data Index: 1051592 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.3973. Min Act: -0.0001

Data Index: 620966 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.5320. Min Act: -0.0000

Data Index: 853582 (C4 (Web Text))

Max Activating Token Index: 681

Text #14

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.5297. Min Act: -0.0000

Data Index: 84372 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.5409. Min Act: 0.0000

Data Index: 1128518 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.5714. Min Act: -0.0000

Data Index: 103746 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.4907. Min Act: -0.0000

Data Index: 1050928 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.5465. Min Act: -0.0001

Data Index: 1221025 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.5127. Min Act: -0.0000

Data Index: 765166 (C4 (Web Text))

Max Activating Token Index: 118