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

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

Neuron 1571 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.4134. Min Act: -0.0000

Data Index: 600835 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3777. Min Act: -0.0000

Data Index: 197345 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3519. Min Act: -0.0000

Data Index: 1287239 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3432. Min Act: -0.0000

Data Index: 625864 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3298. Min Act: -0.0000

Data Index: 394745 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3276. Min Act: -0.0000

Data Index: 114742 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3013. Min Act: -0.0000

Data Index: 359303 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2784. Min Act: -0.0000

Data Index: 1097805 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3086. Min Act: -0.0000

Data Index: 724827 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3168. Min Act: -0.0000

Data Index: 519076 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2976. Min Act: -0.0000

Data Index: 553076 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2946. Min Act: -0.0000

Data Index: 620213 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2886. Min Act: -0.0000

Data Index: 675741 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2939. Min Act: -0.0000

Data Index: 1343749 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2795. Min Act: -0.0000

Data Index: 928300 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2676. Min Act: -0.0000

Data Index: 998906 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2743. Min Act: -0.0000

Data Index: 174660 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2849. Min Act: -0.0000

Data Index: 486822 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2834. Min Act: -0.0000

Data Index: 95204 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2728. Min Act: -0.0000

Data Index: 1037694 (C4 (Web Text))

Max Activating Token Index: 93