Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3935 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.7098. Min Range: -5.7098

Max Act: 5.4922. Min Act: -0.0000

Data Index: 389790 (C4 (Web Text))

Max Activating Token Index: 954

Text #1

Max Range: 5.7098. Min Range: -5.7098

Max Act: 4.9142. Min Act: -0.0000

Data Index: 849311 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 5.7098. Min Range: -5.7098

Max Act: 5.7098. Min Act: -0.0000

Data Index: 362245 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 5.7098. Min Range: -5.7098

Max Act: 5.3210. Min Act: -0.0000

Data Index: 486805 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 5.7098. Min Range: -5.7098

Max Act: 5.2159. Min Act: -0.0000

Data Index: 944879 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 5.7098. Min Range: -5.7098

Max Act: 5.4465. Min Act: -0.0000

Data Index: 862443 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 5.7098. Min Range: -5.7098

Max Act: 5.3942. Min Act: -0.0000

Data Index: 940720 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 5.7098. Min Range: -5.7098

Max Act: 5.0192. Min Act: -0.0000

Data Index: 636888 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 5.7098. Min Range: -5.7098

Max Act: 5.1646. Min Act: -0.0000

Data Index: 1126362 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 5.7098. Min Range: -5.7098

Max Act: 4.9990. Min Act: -0.0000

Data Index: 984305 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 5.7098. Min Range: -5.7098

Max Act: 4.6557. Min Act: -0.0000

Data Index: 536266 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 5.7098. Min Range: -5.7098

Max Act: 4.6637. Min Act: -0.0000

Data Index: 187510 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 5.7098. Min Range: -5.7098

Max Act: 4.2750. Min Act: -0.0000

Data Index: 941163 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 5.7098. Min Range: -5.7098

Max Act: 3.3485. Min Act: -0.0000

Data Index: 421268 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 5.7098. Min Range: -5.7098

Max Act: 3.1535. Min Act: -0.0000

Data Index: 1325757 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 5.7098. Min Range: -5.7098

Max Act: 3.1375. Min Act: -0.0000

Data Index: 1477416 (Python Code)

Max Activating Token Index: 1000

Text #16

Max Range: 5.7098. Min Range: -5.7098

Max Act: 2.8273. Min Act: -0.0000

Data Index: 433160 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 5.7098. Min Range: -5.7098

Max Act: 3.0979. Min Act: -0.0000

Data Index: 525190 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 5.7098. Min Range: -5.7098

Max Act: 3.0267. Min Act: -0.0000

Data Index: 1348583 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 5.7098. Min Range: -5.7098

Max Act: 2.8034. Min Act: -0.0000

Data Index: 1145889 (C4 (Web Text))

Max Activating Token Index: 526