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

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

Neuron 2 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.5767. Min Act: -0.0000

Data Index: 1044303 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.5196. Min Act: -0.0000

Data Index: 966695 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.5479. Min Act: -0.0001

Data Index: 862898 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4970. Min Act: -0.0001

Data Index: 117349 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4638. Min Act: -0.0001

Data Index: 258018 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.3875. Min Act: -0.0001

Data Index: 464509 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.3711. Min Act: -0.0001

Data Index: 875289 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.3444. Min Act: -0.0001

Data Index: 378938 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.3515. Min Act: -0.0001

Data Index: 177251 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.3392. Min Act: -0.0001

Data Index: 55729 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.3156. Min Act: -0.0001

Data Index: 1254723 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.3120. Min Act: -0.0001

Data Index: 433615 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.3293. Min Act: -0.0001

Data Index: 45930 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.3153. Min Act: -0.0000

Data Index: 860283 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.2920. Min Act: -0.0001

Data Index: 964380 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.3020. Min Act: -0.0001

Data Index: 855602 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.3025. Min Act: -0.0001

Data Index: 481944 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.2937. Min Act: -0.0001

Data Index: 676161 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.2932. Min Act: -0.0001

Data Index: 220036 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.3151. Min Act: -0.0001

Data Index: 609563 (C4 (Web Text))

Max Activating Token Index: 285