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

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

Neuron 1259 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.4422. Min Act: 0.0001

Data Index: 1306975 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.4242. Min Act: -0.0001

Data Index: 498738 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3750. Min Act: -0.0001

Data Index: 1338508 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3662. Min Act: -0.0000

Data Index: 871428 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3682. Min Act: -0.0001

Data Index: 53108 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3525. Min Act: 0.0001

Data Index: 890746 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3460. Min Act: -0.0001

Data Index: 65051 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3514. Min Act: -0.0001

Data Index: 135858 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3436. Min Act: -0.0001

Data Index: 1102386 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3421. Min Act: -0.0001

Data Index: 401085 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3273. Min Act: -0.0001

Data Index: 111818 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3303. Min Act: 0.0000

Data Index: 612182 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3380. Min Act: -0.0001

Data Index: 680131 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3377. Min Act: -0.0001

Data Index: 1021958 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3206. Min Act: 0.0000

Data Index: 408140 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3194. Min Act: -0.0001

Data Index: 428506 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3216. Min Act: -0.0000

Data Index: 54308 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3191. Min Act: -0.0001

Data Index: 1061333 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3288. Min Act: -0.0000

Data Index: 673294 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3049. Min Act: -0.0001

Data Index: 469993 (C4 (Web Text))

Max Activating Token Index: 213