Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4881 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.8567. Min Act: -0.0000

Data Index: 1379171 (Python Code)

Max Activating Token Index: 256

Text #1

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.9183. Min Act: -0.0000

Data Index: 1589117 (Python Code)

Max Activating Token Index: 425

Text #2

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.6244. Min Act: -0.0000

Data Index: 1547341 (Python Code)

Max Activating Token Index: 560

Text #3

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.4240. Min Act: -0.0000

Data Index: 1540743 (Python Code)

Max Activating Token Index: 409

Text #4

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.5124. Min Act: -0.0000

Data Index: 1502502 (Python Code)

Max Activating Token Index: 536

Text #5

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.4973. Min Act: -0.0000

Data Index: 1386520 (Python Code)

Max Activating Token Index: 175

Text #6

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.4807. Min Act: -0.0000

Data Index: 1406043 (Python Code)

Max Activating Token Index: 824

Text #7

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.4700. Min Act: -0.0000

Data Index: 1557680 (Python Code)

Max Activating Token Index: 160

Text #8

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.3826. Min Act: -0.0000

Data Index: 1600163 (Python Code)

Max Activating Token Index: 182

Text #9

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.4717. Min Act: -0.0000

Data Index: 1413941 (Python Code)

Max Activating Token Index: 453

Text #10

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.4596. Min Act: -0.0000

Data Index: 1606401 (Python Code)

Max Activating Token Index: 480

Text #11

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.3714. Min Act: -0.0000

Data Index: 1471247 (Python Code)

Max Activating Token Index: 645

Text #12

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.3205. Min Act: -0.0000

Data Index: 1559963 (Python Code)

Max Activating Token Index: 958

Text #13

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.3073. Min Act: -0.0000

Data Index: 1494664 (Python Code)

Max Activating Token Index: 127

Text #14

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.4716. Min Act: -0.0000

Data Index: 1579832 (Python Code)

Max Activating Token Index: 73

Text #15

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.4192. Min Act: -0.0000

Data Index: 1368599 (Python Code)

Max Activating Token Index: 877

Text #16

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.3151. Min Act: -0.0000

Data Index: 1467088 (Python Code)

Max Activating Token Index: 89

Text #17

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.2487. Min Act: -0.0000

Data Index: 1632385 (Python Code)

Max Activating Token Index: 148

Text #18

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.2914. Min Act: -0.0000

Data Index: 1498784 (Python Code)

Max Activating Token Index: 601

Text #19

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.2770. Min Act: -0.0000

Data Index: 1639622 (Python Code)

Max Activating Token Index: 251